US20090110298A1 - System and Method for Compiling Images from a Database and Comparing the Compiled Images with Known Images - Google Patents
System and Method for Compiling Images from a Database and Comparing the Compiled Images with Known Images Download PDFInfo
- Publication number
- US20090110298A1 US20090110298A1 US12/346,988 US34698808A US2009110298A1 US 20090110298 A1 US20090110298 A1 US 20090110298A1 US 34698808 A US34698808 A US 34698808A US 2009110298 A1 US2009110298 A1 US 2009110298A1
- Authority
- US
- United States
- Prior art keywords
- objects
- web
- storage device
- image
- internet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S707/00—Data processing: database and file management or data structures
- Y10S707/99931—Database or file accessing
- Y10S707/99932—Access augmentation or optimizing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S707/00—Data processing: database and file management or data structures
- Y10S707/99931—Database or file accessing
- Y10S707/99933—Query processing, i.e. searching
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S707/00—Data processing: database and file management or data structures
- Y10S707/99931—Database or file accessing
- Y10S707/99933—Query processing, i.e. searching
- Y10S707/99936—Pattern matching access
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S707/00—Data processing: database and file management or data structures
- Y10S707/99941—Database schema or data structure
- Y10S707/99944—Object-oriented database structure
- Y10S707/99945—Object-oriented database structure processing
Definitions
- This invention relates generally to computer networks. More particularly, this invention provides for a system and method for searching and compiling from a database, such as the Worldwide Internet, images that have a specified visual content, and for determining if any of the compiled images are substantially similar to one or more known images.
- a database such as the Worldwide Internet
- a system and method for searching and compiling from a database such as the Worldwide Internet, images that have a specified visual content, and for determining if any of the compiled images are substantially similar to one or more known images.
- a database such as the Worldwide Internet
- What has been more specifically invented is a high-precision, automated visual detection service to protect global trademarks, servicemarks, and brands from infringement, dilution, or tarnishment by look-alike or imposter marks and brands on the Internet.
- the visual detection technology provided by the present invention finds a brand, trademark, or servicemark on Internet web pages, and also finds designs, symbols, shapes, and signs that closely resemble the brand, trademark or servicemark.
- the present invention also identifies logos within a larger picture and text within images.
- the present invention broadly provides a system and method for searching and discovering from a database (e.g., the Worldwide Internet) an object (e.g. a logo, a trademark, etc.) which is confusingly similar with a known object.
- a database e.g., the Worldwide Internet
- an object crawler sweeps websites of the Internet by automatically following hyperlinks contained in the websites.
- the object crawler identifies all objects and duplicates them by downloading them on servers of a temporary storage system.
- the visual content of the objects may be analyzed, such as by hundreds of parallel computers analyzing object content. This may be done in a massive parallel manner with hundreds of computers (e.g., three hundred computers or more).
- Each computer object operates an object analysis software component which processes one or more input objects and produces as output descriptive information in terms of text and numbers about what content is in the object(s). For each object the following information may be produced and stored: object size; “fingerprint” for efficient identification of substantial similar objects; all text contained in the object(s); “fingerprint” of each face contained in the object(s); information about the logos/trademarks contained in the object(s); and information about things and images contained in the object(s).
- a graphical user interface where the user may enter search criteria for the object to be searched.
- the search criteria to be entered in the graphical user interface may include one or more of the following search criteria: (i) one or more text strings that may be contained in the object including any image; (ii) one or more logo, trademarks or servicemarks selected from a list of predefined logos, trademarks or servicemarks that may be contained in the object including any image; (iii) one or more things or physical features or shapes selected from a list of predefined logos, trademarks or servicemarks that may be contained in the object including any image; (iv) one or more faces of facial templates that may be contained in the object including any image; and (v) one or more images that look substantially similar.
- a system and method for searching for an entity's logos, trademarks or servicemarks in objects and images in the Worldwide Internet.
- a known logo and/or trademark and/or servicemark is provided and is entered into the system of the present inventions; and the content of each object in the internet is compared with the known logo and/or trademark and/or servicemark to determine if there is any confusing similarity. If a confusingly similar logo and/or trademark and/or servicemark appears in the internet object, a reference to the internet object is stored as search results. After scrutinizing objects in the internet, the user may access the search results.
- a system and method for searching for faces of people or animals that are substantial identical to a known face.
- the system and method of embodiments of the present invention accept as input an object (e.g., a scanned photograph) that contains at least one face. Subsequently, the input face is compared with all faces in the internet objects (including images) using already computed face “fingerprints” available in storage. The result of the comparison is output in the form of a list of substantial identical objects (including images) that contain a face that is similar or substantially identical to the input face.
- Embodiments of the present invention more specifically provide a method for discovering from a database (e.g., the Worldwide Internet) an object which is confusingly similar with a known object comprising: (a) searching (e.g. searching with a web crawler by following hyperlinks contained in web site elements) a database for objects; (b) providing a known object; and (c) determining if any object from the database is confusingly similar with the known object.
- the method preferably additionally comprises duplicating the objects from the database to produce duplicated objects; storing the duplicated objects to produce stored duplicated objects; and determining if any stored duplicated object is confusingly similar with the known object.
- the method further preferably additionally comprises determining the degree of similarity of any stored duplicated object with the known object.
- the objects may be selected from the group consisting of graphic images, videos, audio sounds and mixtures thereof.
- Each of the objects may be an intellectual property selected from the group consisting of logos, trademarks, service marks, and mixtures thereof.
- Determining if any object is confusingly similar with the known object further preferably comprises determining if all of the necessary metadata is available for any of the stored duplicated objects; and if not, the necessary metadata is developed for the stored duplicated objects. Determining if any object is confusingly similar with the known object further preferably comprises performing one or more of the following process steps: conducting an optical character recognition analysis on the object; conducting a facial analysis on the object; conducting a watermark analysis on the object; conducting a signature analysis on the object; and conducting an object similarity analysis on the object.
- Embodiments of the present invention also more specifically provide a method comprising accessing a store that is storing duplicated objects from a database (e.g., an Internet database); and determining if any of the duplicated objects stored in the store are similar with a known object.
- a database e.g., an Internet database
- Embodiments of the present invention further also more specifically provide a computer-readable storage medium storing program code for causing a processing system to perform the steps of: searching a database for objects; duplicating the objects from the database to produce duplicated objects; storing (e.g., maintaining in memory or transferring into memory) the duplicated objects to produce stored duplicated objects; determining if any stored duplicated object is confusingly similar with a known object.
- Embodiments of the present invention also provide for a system for discovering from a database an object which is confusingly similar with a known object comprising: a search engine for searching a database for objects; a duplicator coupled to the search engine for duplicating objects from the database to produce duplicated objects; a store coupled to the duplicator for storing the duplicated objects to produce stored duplicated objects; and determining means, coupled to the store, for determining if any stored duplicated object is confusingly similar with a known object.
- the system additionally preferably comprises determining the degree of similarity of any stored duplicated object with the known object.
- the present invention further also provides a system for discovering from a database an object which is confusingly similar with a known object comprising: means for searching a database for objects; means for duplicating objects from the database to produce duplicated objects; means for storing the duplicated objects to produce stored duplicated objects; and means for determining if any stored duplicated object is confusingly similar with a known object.
- the system additionally preferably comprises means for determining the degree of similarity of any stored duplicated object with the known object.
- the present inventions also provides a method for determining a degree of similarity between a known object and an object duplicated from a database comprising: duplicating an object from a database to produce a duplicated object; analyzing the content of the duplicated object (e.g., by assigning numbers for each pixel in the duplicated object) to produce a matrix of numbers; producing a model template from a known object; and comparing the model template of the known object with the matrix of numbers to determine the degree of similarity between the duplicated object and the known object.
- the method for determining a degree of similarity between a known object and an object duplicated from a database preferably additionally comprises one or more of the following process steps: providing a threshold degree of similarity to set a standard for confusingly similarity between the known object and the duplicated object; displaying the degree of similarity if the degree of similarity is at least equal to the threshold degree of similarity; and determining what region of the object the known object is located.
- the matrix of numbers is created in a RAM when the object (or image) is loaded from storage.
- the model template is computed and/or created automatically when the first search for object (e.g., a logo) is executed.
- the model template may be stored in a RAM. Each pixel consists of three numbers representing red, green, and blue. Color depends on algorithms.
- the colored image is converted into a grayscale image; subsequently, the actual analysis (or object/image detection) is performed on the grayscale image.
- FIG. 1 is a block diagram illustrating a user network access system in accordance with the present invention
- FIG. 2 is a block diagram illustrating details of a company computer system
- FIG. 3A is a schematic diagram of a web crawler coupled to the Internet and its associated servers and further coupled to an object analyzer and storage device;
- FIG. 3B is a schematic diagram of a web crawler coupled to the Internet and to an object analyzer and storage device;
- FIG. 4 is a block diagram of a RAM device including an operating system, a communication engine, and a browser;
- FIG. 5 is a block diagram for an embodiment of the web crawler
- FIG. 6 is a block diagram for another embodiment of the web crawler
- FIG. 7 is a block diagram for an embodiment of the object analyzer and storage device
- FIG. 8 is a block diagram for another embodiment of the object analyzer and storage device.
- FIG. 9 is a flowchart in accordance with an embodiment of the invention broadly illustrating a method for sweeping or canvassing a database, such as the Worldwide Internet, for detecting, duplicating, and storing objects (e.g., images, videos, and audio sounds);
- a database such as the Worldwide Internet
- FIG. 10 is a flowchart in accordance with an embodiment of the invention broadly illustrating a method for broadly analyzing objects stored after being duplicated from a database, such as the Worldwide Internet;
- FIG. 11 is a flowchart in accordance with an embodiment of the invention for illustrating a method for more specifically analyzing the stored objects from FIG. 10 ;
- FIG. 12 is a flowchart in accordance with an embodiment of the invention for illustrating a method for analyzing an image after the stored object has been determined to be an image in accordance with the method schematically illustrated in FIG. 11 ;
- FIG. 13 is a flowchart in accordance with an embodiment of the invention for illustrating a method for analyzing and determining similarity of a known logo with one or more stored logos duplicated from a database, such as the Worldwide Internet;
- FIG. 14 is a flowchart in accordance with another embodiment of the invention broadly illustrating a method for online sweeping or canvassing a database for online detecting, analyzing, duplicating, and storing objects;
- FIG. 15 is a flowchart broadly illustrating a method for adding and storing URLs which are to be searched in a database
- FIG. 16 is a flowchart in accordance with another embodiment of the invention for illustrating a method for online analyzing and determining similarity of a known logo with any logo detected and analyzed in a database, such as the Worldwide Internet;
- FIG. 17 is a pictorial of an image-object for Example I that was duplicated from the Internet and stored in the object storage device.
- FIG. 18 is a pictorial of a known image that was used in Example II to determine if any of the images contained in object storage device were substantially similar to the known image.
- System 100 includes a company computer system, generally illustrated as 104 , a plurality of servers, generally illustrated as 108 , and an interconnected networks of computers (“Internet”) generally illustrated as 112 , for coupling the company computer system 104 to the plurality of servers 108 which include a plurality of web site elements, generally illustrated as 113 .
- the servers 108 may include any number of servers, such as servers 108 a , 108 b , 108 e , and 108 d .
- the plurality of web site elements 108 represent web site elements for each server 108 a , 108 b , 108 e , and 108 d .
- Each server 108 a , etc, and its associated web site elements 108 are typically coupled to a respective computer (not shown) via an internal network signal bus (not shown), and represents a respective possessor or owner of a web page system for advertisement, informational purposes, services, etc., on the Internet 112 .
- Exemplary advertisement, informational purposes, and services include promotional services, sales information, biographical information, e-mail service programs, address book service programs, calendar service programs, paging service programs, and company database service programs, etc., all of which may include audio sounds, videos, and one or more graphic images (e.g., a reproduction or imitation of a design and text or words including a reproduction or imitation of a person, a thing, a mark, or a symbol) including logos (e.g. non-word elements, a design such as graphic designs, etc), trademarks (e.g., a word, symbol or device pointing distinctly to the origin or ownership of merchandise to which it is applied and legally reserved to the exclusive use of the owner as maker or seller), service marks (e.g.
- objects comprise images, videos, audio sounds, and the like.
- URL Uniform Resource Locator
- the computer system 104 includes a processor 210 (e.g., a Central Processing Unit) such as a Motorola Power PC®) microprocessor or an Intel Pentium® microprocessor.
- An input device 220 such as keyboard and mouse, and an output device 230 , such as a Cathode Ray Tube (CRT) display, are coupled via a signal bus 240 to processor 210 .
- a communications interface 250 a data storage device 260 , such as Read Only Memory (ROM) or a magnetic disk, and a Random-Access Memory (RAM) 270 are further coupled via signal bus 240 to processor 210 .
- ROM Read Only Memory
- RAM Random-Access Memory
- the communications interface 250 of the computer system 104 is coupled to the Internet 112 as shown in and described with reference to FIG. 1 .
- the computer system 104 also includes an operating system 280 , a web crawler 284 , an object storage device 248 , analyzer parametric Rules 288 for determining similarity, object analyzer and storage device 290 , and a downloading engine 292 .
- FIG. 3A there is seen a schematic diagram of the web crawler 284 coupled to the Internet 112 (including the servers 108 ), and to both the data storage device 260 and the object storage device 248 which latter both in turn are coupled to the object analyzer and storage device 290 .
- the web crawler 284 “walks through” the Internet 112 and sweeps the servers 108 , searching for web objects including images, by automatically following hyperlinks contained in the respective web site elements 113 .
- the web crawler 284 may go to any web site, including specified web sites that are not linked (e.g., top level domains (TLD)).
- TLD top level domains
- the web crawler 284 may also temporarily store URLs, hyperlinks, and copies of objects.
- An object transfer engine (identified below as “ 440 ” and “ 550 ”) may then respectively transfer the web objects and the URLs of the objects to data storage device 260 and to object storage device 248 .
- Each object contains pixels (e.g. 10,000 or more pixels) and numbers are assigned to each pixel when the object is being analyzed by content.
- the object analyzer and storage device 290 are coupled to a display or output device 320 and includes the analyzer parametric Rules 288 for determining similarity and the downloading engine 292 for downloading the web objects and the URLs from the data storage device 260 and the object storage device 248 , respectively.
- object analyzer and storage device 290 wherein web objects may be analyzed and wherein descriptive information about the content of each web object may be stored.
- object analyzer and storage device 290 analyzes web objects by number of pixels in each web object and assigns numbers for each pixel and stores the numbers (i.e., the descriptive information about content of each object). Each pixel consists of three (3) numbers representing the colors red, green, and blue.
- the web crawler 284 is coupled directly to the object analyzer and storage device 290 , instead of being coupled to the object analyzer and storage device 290 via object storage device 248 and data storage device 260 .
- Image or object analysis components employed by the analyzer 290 for each object include, but is not limited to, text (e.g. words and the like), logos, faces (e.g., both human and animal faces, and the like), and two dimensional objects or things (e.g., cars, planes, animals, and the like), and combinations thereof.
- the operating system 280 has a program for controlling processing by processor 210 , and may be stored at any suitable location (e.g., in object storage device 260 ) and is loaded by the downloading engine 282 into RAM 270 for execution (see FIGS. 2 and 4 ). As best shown in FIG. 4 , operating system 280 includes or controls a communication engine 282 for generating and transferring messages including objects to and from the Internet 112 via the communications interface 250 . Operating system 280 further includes or controls an internet engine such as a web browser 246 , e.g., the NetscapeTM web browser produced by Netscape, and the Internet ExplorerTM web browser produced by the Microsoft Corporation.
- a web browser 246 e.g., the NetscapeTM web browser produced by Netscape, and the Internet ExplorerTM web browser produced by the Microsoft Corporation.
- the web browser 246 may comprise an encryption or decryption engine (not shown in the drawings for encrypting or decrypting messages).
- the browser 246 further receives web page data including web objects and/or other desired information.
- the web browser 246 enables a user of the computer system 104 to receive objects including images from the servers 108 via the Internet 112 .
- the system 100 may also include additional information, such as network connections, additional memory, additional processors, Local Area Networks (LANs), input/output lines for transferring information across a hardware channel, the Internet 112 or an intranet, etc.
- additional information such as network connections, additional memory, additional processors, Local Area Networks (LANs), input/output lines for transferring information across a hardware channel, the Internet 112 or an intranet, etc.
- programs and data may be received by and stored in the system in alternative ways.
- a computer-readable storage medium (CRSM) reader such as a magnetic disk drive, hard disk drive, magneto-optical reader, CPU, etc. may be coupled to the signal bus 240 for reading a computer-readable storage medium (CRSM) such as a magnetic disk, a hard disk, a magneto-optical disk, RAM, etc.
- CRSM computer-readable storage medium
- the system 100 may receive programs and data via a CRSM reader.
- memory herein is intended to cover all data storage media whether permanent or temporary. Therefore, it will be apparent to those skilled in the art that several variations of the system elements are contemplated as being within the intended scope of the present invention. For example, given processor and computer performance variations and ongoing technological advancements, hardware elements (e.g., multiplexers, etc.) may be embodied in software or in a combination of hardware and software. Similarly, software elements may be embodied in hardware or in a combination of hardware and software.
- connection to other computing devices may take place at output device 230 or communications interface 250
- wired, wireless, modem and/or connection or connections to other computing devices might be utilized.
- other computing devices including but not limited to local area networks, wide area networks and the Internet 112
- connection to other computing devices might be utilized.
- other computing devices including but not limited to local area networks, wide area networks and the Internet 112
- the use of distributed processing, multiple site viewing, information forwarding, collaboration, remote information retrieval and merging, and related capabilities are each contemplated.
- Various operating systems and data processing systems can also be utilized, however at least a conventional multitasking operating system such as Windows95® or Windows NT® (trademarks of Microsoft, Inc.) running on an IBM® (trademark to International Business Machines, Inc.) compatible computer is preferred and will be presumed for the discussion herein.
- Input device 220 can comprise any number of devices and/or device types for inputting commands and/or data, including but not limited to a keyboard, mouse, and/or speech recognition.
- the web crawler 284 of the present invention sweeps or “walks through” the Internet 112 including servers 108 by automatically following hyperlinks contained in the respective web site elements 113 , or by going to specific web sites that are not linked, such as top level domains (TLD).
- the web crawler 284 on each web site identifies all web objects and duplicates or copies them from the servers 108 and Internet 112 .
- FIGS. 5 and 6 represent two respective embodiments for the web crawler 284 . Referring to FIG.
- the web crawler 284 as including crawler Rules 406 for determining or identifying web objects on the web, an object search engine 410 for searching all of the servers 108 for web objects in accordance with the crawler Rules 406 , a URL storage device 420 for storing Uniform Resource Locators for each of the web sites, and an object storage device 430 for receiving and temporarily storing web objects that have been identified by the web crawler 284 in accordance with the crawler Rules 406 .
- crawler Rules 406 for determining or identifying web objects on the web
- an object search engine 410 for searching all of the servers 108 for web objects in accordance with the crawler Rules 406
- a URL storage device 420 for storing Uniform Resource Locators for each of the web sites
- an object storage device 430 for receiving and temporarily storing web objects that have been identified by the web crawler 284 in accordance with the crawler Rules 406 .
- the web crawler 284 of FIG. 5 may also include an object transfer engine 440 for transferring the stored web objects from the object storage device 430 to an object data base, such as web object storage device 248 , as well as a URL transfer engine 450 for transferring Uniform Resource Locators from URL storage device 420 to a URL data base, such as data storage device 260 .
- the web crawler 284 of FIG. 5 continually monitors the entire Internet 112 including the servers 108 for any and all web objects.
- this embodiment of the web crawler 284 continually scavenges the Internet 112 including the servers 108 coupled thereto for any and all web objects without making any discernment as to substantial similarity between any object on the Internet 112 and/or servers 108 and any known object.
- This embodiment of the web crawler 284 includes a URL storage device 510 for storing Uniform Resource Locators for each of the web sites, and an object-to-be-searched storage device 520 which receives and stores web objects that are to be searched on the Internet 112 and servers 108 by the web crawler 284 .
- the user of this embodiment of the web crawler 284 enters or inputs the desired known objects into the object-to-be searched storage device 520 whose substantially similarity is to be searched for on the Internet 112 and servers 108 .
- This embodiment of the web crawler 284 also includes crawler Rules 526 for determining substantial similarity between the known object(s) stored in the object-to-be searched storage device 520 and any web objects discovered on the Internet 112 and/or servers 108 .
- the web crawler 284 of FIG. 6 further also includes an object search and comparison engine 530 , an objects-copied-from-web storage device 540 , an object transfer engine 550 and a URL transfer engine 560 .
- the object search and comparison engine 530 searches in accordance with crawler Rules 526 , the Internet 112 and servers 108 for known objects that are stored in the object-to-be-searched storage device 520 .
- the engine 530 also compares in accordance with the crawler Rules 526 each web object found on the Internet 112 and/or servers 108 with each known object stored in the object-to-be-searched storage device 520 ; and if there is a substantial similarity in accordance with the crawler Rules 526 , the engine 530 downloads (i.e., duplicates or copies) the substantially similar web object(s) off of the Internet 112 and servers 108 into the objects-copied-from-web storage device 540 .
- the object transfer engine 550 duplicates and transfers the substantially similar web object(s) from the objects-copied-from-web storage device 540 to a data base, such as object storage device 248 .
- the URL transfer engine 450 transfers Uniform Resource Locators from URL storage device 510 to a URL data base, such as data storage device 260 .
- the web crawler 284 of FIG. 6 selectively searches the Internet 112 including the servers 108 for any web objects that are substantially similar to the known object(s) stored in the object-to-be-searched storage device 520 .
- the web crawler 284 scavenges the Internet 112 and the servers 108 with discernment, looking for any and all web objects that are substantially similar to any and all known objects stored in the object-to-be-searched storage device 520 .
- FIG. 7 and FIG. 8 there is seen two respective embodiments for the object analyzer and storage device 290 .
- the object analyzer and storage device 290 as including the analyzer parametric Rules 288 for determining similarity, an analyzer object comparison engine 730 , the downloading engine 292 , and a descriptive information storage device 710 .
- the descriptive information storage device 710 contains descriptive information (i.e., mathematical model templates) about one or more known objects for making a determination if the known objects are substantially similar to any of the web objects that were duplicated or copied from the Internet 112 or servers 108 by the web crawler 284 .
- the analyzer parametric Rules 288 for determining similarity are the rules and parameters that the object analyzer and storage device 290 employs to determine if there is substantial similarity between the descriptive information pertaining to the known objects stored in the descriptive information storage device 710 and the web objects, more specifically the information on the web objects, which is stored in the object storage device 248 after being removed or extracted from the Internet 112 and/or servers 108 .
- the web-copied or web-duplicated web objects are subsequently either initially stored in object storage device 430 , or in the objects-copied-from-web storage device 540 , or the web-copied web objects bypass these crawler storage sections and are loaded directly into the object storage device 248 .
- the downloading engine 297 is capable of downloading web objects (including associated descriptive information on web objects) and URLs from object storage device 248 and data storage device 260 , respectively, into the object analyzer and storage device 290 , more specifically into the analyzer object storage device 720 of the object analyzer and storage device 290 where the downloaded information is converted into a plurality of numbers from the number of pixels in each web object.
- each pixel in an object is given particular numbers producing a set of numbers which are compared with the mathematical model template of the known object for determining a degree of similarity.
- Each pixel consists of three (3) numbers representing the colors red, green, and blue.
- a separate downloading engine (not shown) is employed for downloading URLs from the data storage device 260 into the analyzer object storage device 720 of the object analyzer and storage device 290 .
- the analyzer object comparison engine 730 makes a comparison between the downloaded web objects (including their associated descriptive information which is in the form of a matrix of numbers from pixels) and the descriptive information (i.e., a template such as a mathematical model template) concerning one or more known objects in the descriptive information storage device 710 .
- the descriptive information i.e., a template such as a mathematical model template
- a match is made between one or more of the downloaded web objects and one or more of the known objects.
- This information including the corresponding URL(s) for the downloaded web objects may then be provided or displayed through any suitable output device 320 , including a printer or video screen or any of the like.
- the degree of similarity may also be provided or displayed.
- the analyzer parametric Rules 288 , or the analyzer parametric Rules 288 in combination with the analyzer object comparison engine 730 enable the degree of similarity between downloaded web objects and known objects to be determined.
- Typical degree of similarity would be 100%, 95%, 90%, 85%, 80%, or any suitable degree of similarity that is desired.
- the degree of similarity is preferably determined by comparing a mathematical model template of the known object with a matrix of numbers generated from the number of pixels in each web object, with each pixel consisting of three numbers representing the colors red, green, and blue. The manner in which color in an object or image is addressed depends on each algorithm. For example, in the logo search exemplified in FIG. 13 , a colored image is converted into a grayscale image; then the actual analysis/logo detection is performed on the grayscale image.
- the matrix of numbers is computed in a RAM, such as RAM 270 , when the object or image is loaded from storage, such as storage device 248 .
- FIG. 8 there is seen another embodiment of the object analyzer and storage device 290 as including analyzer object comparison engine 830 , and an (optional) analyzer parametric Rules 840 , preferably for “fine tuning” or tweaking any determination of similarity made by the web crawler 284 , more specifically the web crawler 284 of FIG. 6 .
- the analyzer parametric Rules 840 may be optional in the sense that analyzer parametric Rules 840 may not be needed if the crawler Rules 526 , or if the crawler Rules 526 in combination with the object search and comparison engine 530 , are sufficient enough such that the web objects stored in the objects-copied-from-web storage device 540 has the desired degree of similarity with the known objects stored in the object-to-be-searched storage device 520 . In such a case the web-copied or web-duplicated web objects may be displayed through the output or display device 390 (see FIG. 3B ), such as any suitable printer and/or video screen or the like.
- the crawler Rules 526 may also furnish the degree of similarity between web objects in the objects-copied-from-web storage device 540 and the known objects in the objects-to-be-searched storage device 520 .
- the analyzer parametric Rules 840 or the analyzer parametric Rules 840 in combination with the comparison engine 830 , would be employed for “fine tuning” or tweaking the determination of similarity determined by the crawler 284 of FIG. 6 , more specifically by the crawler Rules 526 , or by the crawler Rules 526 in combination with the object search and comparison engine 530 , of FIG. 6 .
- the degree of similarity detected by the crawler 284 of FIG. 6 is say 50%, then the object analyzer and storage device 290 of FIG.
- the analyzer parametric Rules 840 may be used to “fine tune” or tweak this 50% degree of similarity to produce a more sufficient degree of similarity. More specifically, the analyzer parametric Rules 840 , or the analyzer parametric Rules 840 and the comparison engine 830 in combination with the information contained in the descriptive information storage device 710 , for the object analyzer and storage device 290 of FIG. 8 would be employed to produce a higher degree of similarity (e.g., 90%) between the web object(s) and the known object(s).
- a higher degree of similarity e.g. 90%
- the object analyzer and storage device 290 of FIG. 8 may also (optionally) include the downloading engine 292 . If the embodiment of the invention in FIG. 3B is employed such that the web crawler 284 is coupled directly to the object analyzer and storage device 290 , instead of being coupled via object storage device 248 and data storage device 260 , the downloading engine 292 would not be necessary as the object transfer engine 550 of the web crawler could directly transfer any web objects recovered from the Internet 112 and the servers 108 to the analyzer object storage device 820 .
- the object analyzer and storage device 290 of FIG. 8 also has the descriptive information storage device 710 and an analyzer object storage device 820 which functions comparably to the analyzer object storage device 720 .
- Storage steps 1000 stores with priorities all URLs whose associated web pages are to be searched by web crawler 284 .
- Step 910 removes from storage device 1000 a an URL with the highest priority. After removal of the highest priority URL, the web crawler 284 finds the highest priority URL in the Internet 112 and searches for a web page associated with the highest priority URL.
- the web crawler 284 in step 920 determines that there is no web page associated with the highest priority URL, then the second highest priority URL is removed from storage device 1000 a and the web crawler 284 repeats the determining step 920 for the second highest priority URL; that is, the web crawler 284 finds the second highest priority URL in the Internet 112 and searches for a web page associated with the second highest priority URL. If the web crawler 284 in step 920 determines that there is no web page associated with the second highest priority URL, the procedure is repeated for a third highest priority URL in storage device 1000 a , and so forth. Alternatively, the web crawler 284 in step 920 determines if there are any more URLs in storage device 1000 a to be searched. In other words, is storage device 1000 a empty of URLs to be searched?
- the web page 930 is copied and downloaded by step 940 into web crawler 284 .
- all features or elements of the web site or web page 930 are analyzed in analyzing step 950 in accordance with crawler Rules 406 for determining objects in the downloaded web site or web page 930 .
- An element of a web site or web page 930 is any hypertext mark-up language (HTML) element by definition. HTML is the standard procedure for writing a web site. Stated alternatively, web crawler 284 analyzes the downloaded web site or web page 930 associated therewith for objects.
- Step 960 determines if any hyperlinks are discovered for any element; and, if so, the hyperlinks are stored by storage step 1000 (e.g., in storage device 1000 a ). Stated alternatively further, the web crawler 284 determines from its associated downloaded web page 930 if any of the elements contained therein include hyperlinks associated therewith; and, if so, the hyperlinks are transferred or downloaded to the storing step 1000 (e.g., downloaded into storage device 1000 a ). Hyperlinks effectively execute a “Go To” address wherein the address is the URL associated with the hyperlink. If no hyperlinks are discovered in any particular element by determining step 960 , then determining step 970 determines if the particular element in the downloaded web site or web page 930 includes an object.
- determining step 980 determines if any more elements remain in the downloaded web site or web page 930 . Stated alternatively, the web crawler 284 determines if the last element in the downloaded web page 930 has been tested by determining steps 960 and 970 . If more elements remain, then the next-in-line element is received and determining steps 960 and 970 are performed on the next-in-line element. If the last element of the downloaded web page 930 has been addressed by determining steps 960 and 970 , then the method 900 is repeated for the next highest priority URL from the storage step 1000 (i.e., from storage device 1000 a ).
- step 1020 the first object to be analyzed for similarity with a known object is removed from the object storage device 248 . After removal, a determination is made by determining step 1030 if all of the necessary metadata (i.e., description information data that describes the object which is preferably a matrix of numbers, with numbers representing a pixel in any stored object) is available for the object.
- the metadata or a matrix of numbers generated from pixels for any particular stored object is in metadata storage device 1003 .
- Determining step 1030 searches metadata storage device 1003 for metadata for any particular object. If the necessary metadata for the particular object is not available, then the object is analyzed in step 1001 to develop the necessary metadata.
- object analyzer 1001 develops the necessary metadata by receiving the particular object as input and analyzing that particular object for content (i.e., for metadata content). When the object is a video, each frame of the video will be analyzed for metacontent. Thus, videos are handled as multiple images.
- a storing step 1040 stores the developed metadata.
- the developed metadata is stored in metadata storage device 1003 .
- step 1050 which is to determine if more objects exist for analyzing. More specifically, a determination is made in step 1050 if object storage device 248 contains more objects which are to be tested to determine if the necessary metadata is available for the particular object. If more objects are available to by analyzed, then step 1060 retrieves the next object from storage device 248 and steps 1030 , 1001 , 1040 and 1050 are repeated for the next object until determining step 1050 determines that no more objects exist or are available for analysis.
- FIG. 11 there is seen a flowchart for broadly illustrating the method step 1001 for developing the necessary metadata for any particular object.
- Object 1109 to be analyzed is input, or otherwise provided, for determining in determining step 1110 if the object 1109 is a video. If object 1109 is not a video then the object 1109 is investigated in determining step 1120 to determine if the object 1109 is an image (e.g., both the texts or words and logos or designs of marks). If the object 1109 is a video then step 1130 analyzes each frame of the video. For each frame in the video, step 1130 employs image analyzer 1002 for analysis and recognition operations on each frame. The results of performing an image analysis and an image recognition operation on each frame of an object video is collected by step 1140 and is transferred in the form of metadata to output step 1150 for storage in step 1040 (see FIG. 10 ).
- the image analyzer 1002 is employed in step 1130 for analyzing each frame of a video after determining step 1110 determines that the object is a video, or the image analyzer 1002 is employed in step 1160 (i.e., the image analyzing step 1160 ) after step 1120 determines that the object itself is an image, e.g., the combination of designs or logos and texts or words in a mark, or the combination of two or more of the following in a mark: texts, logos, facial features, watermarks, signature features, and similarity features.
- the image analyzer 1002 for embodiments of the present invention performs one or more of the following analyses: OCR (optical character recognition) analysis which recognizes text (e.g., one or more words) in the image; face analysis which detects human or animal faces by employing templates stored in a storage step (identified below as “ 1005 ”); watermarks analysis which detects and reads embedded watermarks; signature analysis which produces a “digital fingerprint” of the image by calculating one or more numbers, and is employed to identify similar images that have similar “digital fingerprints;” and image similarity analysis which computes one or more numbers that describe the visual similarity of the image to or vis-a-vis images stored in a storing step (identified below as “ 1006 ”).
- OCR optical character recognition
- Each calculated number for signature analysis and for image similarity analysis represents an algorithmic output from a respective algorithm.
- the algorithms adjust for size and orientation (e.g., vertical or horizontal) of the object or image.
- the results computed by and/or obtained by the image analyzing step 1160 e.g., the image analyzer 1002
- the results collected by collecting step 1140 of step 1130 are transferred to storing step 1150 were object metadata is stored.
- FIG. 12 there is seen a flow chart in accordance with an embodiment of the invention for illustrating method 1002 for analyzing an image after step 1120 determines that the object is an image, or for analyzing an image in any frame of a video in accordance with step 1130 .
- Input step 1210 inputs the image to commence one or more of the following analyzing steps: OCR analyzing step 1220 , face analyzing step 1230 , logo analyzing step 1240 , watermarks analyzing step 1250 , signature analyzing step 1260 , and image similarity analyzing step 1270 .
- Analyzer parametric Rules 288 are stored (e.g., storage device 288 a stores analyzer parametric Rules 288 ).
- Rules 288 enable the production of image metadata by communicating with and transferring to steps 1220 , 1230 , 1240 , 1250 , 1260 , and 1270 algorithms and/or other parameters which the steps may employ to assist in producing image metadata.
- OCR analyzing step 1220 receives the pertinent algorithms from analyzer parametric Rules 288 for producing a plurality of numbers (i.e., OCR algorithmic outputs).
- one algorithm received from analyzer parametric Rules 288 may be “Caere OCR” which may be purchased commercially from Caere Corporation of Los Gatos, Calif.
- the analyzing steps employ algorithms which adjust for size and orientation of objects or images.
- the face analyzing step 1230 is conducted on the image by receiving the relevant algorithms from analyzer parametric Rules 288 to enable step 1230 is produce the algorithmic outputs (i.e., numbers) for describing any face.
- analyzer parametric Rules 288 for analyzing a face may be “Face-It” which may be purchased commercially from Caere Corporation of Los Gatos, Calif.
- Facial templates e.g., faces to be searched for on Internet 112
- step 1004 e.g., in storage device 1004 a ).
- the logo analysis step 1240 is conducted on the image.
- Logo templates e.g., logos to be searched for on the Internet 112
- storing step 1005 e.g., in storage device 1005 a
- logo analysis step 1240 analyses any logos (e.g. design(s) or symbol(s) in a mark) within the image versus the logo templates in storage device 1005 a .
- a logo template from storage device 1005 a is superimposed over any logo in the image and is similarly produced by template matching.
- a watermark analysis may subsequently be conducted on the image by the watermarks analysis step 1250 which receives the relevant algorithms and other parameters from analyzer parametric Rules 288 for detecting and reading embedded watermarks in the image.
- an algorithm used in the watermarks analysis step 1250 is Digimark Watermarking which is commercially available from Digimark Corporation of Portland Oreg.
- a signature analysis step 1260 and an image similarity step 1270 is performed on the image.
- the signature analysis step 1260 receives the pertinent and relevant algorithms from the analyzer parametric Rules 288 and inputs into the algorithms detected variables, such as “color count” and “color distribution” to calculate one or more numbers to produce a “digital fingerprint” which are employed to identify images (i.e., known similar images) that have similar “digital fingerprints.”
- the image similarity analysis step 1270 receives the pertinent, relevant algorithms for computing one or more numbers (e.g., algorithmic output(s) such as “Color-Histogram-Matching”) that describe the visual similarity if any to images in storing step 1006 .
- Step 1320 receives known logo 1310 as input logo-to-search. Stated alternatively, a determination is to be made if known logo 1310 is being used on the Internet 112 ; more specifically, if the Internet 112 contains a logo (which could exist in storage device 1005 a ) that is confusingly similar to the known logo 1310 .
- step 1310 From input step 1320 , logo 1310 is duplicated and stored by step 1330 in storing step 1005 (i.e., logo storage device 1005 a ).
- step 1340 executes method 1007 of FIG. 10 (i.e., the object analyzing process 1007 ) to determine if any logos stored in object storage device 248 are confusingly similar to the known logo 1310 .
- Step 1340 uses the object analyzer 1001 to analyze all objects stored in object storage device 248 .
- Method step 1340 may be distributed on hundreds of parallel computers.
- step 1350 displays the results, along with displaying for the similar logos the corresponding metadata and URL from storage device 1003 and database storage 260 for URLs, respectively.
- FIG. 14 there is seen a flow chart for broadly illustrating a method 1400 for online sweeping or canvassing a database, such as internet 112 , for online detecting, analyzing, duplicating, and storing objects.
- the web crawler 284 includes its own object analyzer.
- Storage step 1000 stores with priorities all URLs whose associated web pages are to be searched by web crawler 284 .
- Step 1410 removes from storage 1000 a an URL with the highest priority. After removal of the highest priority URL, the web crawler 284 finds the highest priority URL in the Internet 112 and searches for a web page associated with the highest priority URL.
- the second highest priority URL is removed from storage 1000 a and the web crawler 284 repeats the determining step 1420 for the second highest priority URL; that is, the web crawler 284 finds the second highest priority URL in the Internet 112 and searches for a web page associated with the second highest priority URL. If the web crawler 284 in step 1420 determines that there is no web page associated with the second highest priority URL, the procedure is repeated for a third highest priority URL in storage 1000 a.
- the web page 1430 is copied and downloaded by step 1440 into web crawler 284 .
- all features or elements of the web site or web page 1430 are analyzed in analyzing step 1450 in accordance with crawler Rules 406 for determining objects in the downloaded web site or web page 1430 .
- an element of a web site or web page 1430 is a defined HTML element.
- the web crawler 284 includes its own object analyzer for performing analyzes of the downloaded web site or web page 1430 for objects associated therewith.
- Step 1460 of step 1450 determines if any hyperlinks are discovered for any element, and if so, the hyperlinks are stored by storage step 1000 (e.g., in storage device 1000 a ). Stated alternatively, step 1460 of step 1450 of the web crawler 284 determines from associated downloaded web page 930 if any of the elements contained therein include hyperlinks associated therewith; and if so, the hyperlinks are transferred or downloaded to the storing step 1000 (e.g., downloaded into storage device 1000 a ). As previously indicated, hyperlinks effectively execute a “Go To” address wherein the address is the URL associated with the hyperlinks.
- determining step 1470 determines if the particular element in the downloaded web site or web page 1430 includes an object (e.g., an image, an audio, or video). If one or more objects are found in the particular element being tested, then step 1001 (i.e., method 1001 of FIG. 11 ) is executed for the one or more objects. Step 1480 transfers and/or causes the results to be stored in object metadata storage device 1003 . Subsequently, step 1485 determines if any more URLs exist in storage step 1000 (i.e., storage device 1000 a ) having a second highest priority.
- object e.g., an image, an audio, or video
- step 1485 tests to determine if storage device 1000 a is empty (i.e., have all URLs been removed for analyzing their associated web pages for objects?). If more URLs exist in storage device 1000 a , then step 1490 retrieves the next highest priority URL from storage device 1000 a and steps 1440 and 1450 are repeated for the next highest priority URL from the storing step 1000 (i.e., from storage device 1000 a ).
- step 1510 A new URL is received as input in step 1510 , and then step 1520 transfers and/or otherwise causes the new URL to be stored in the storing step 1000 (i.e., in storage device 1000 a ).
- the first new URL being stored in storage device 1000 a has the highest priority, followed by the second new URL which has the next highest priority, and so forth.
- FIG. 16 there is seen a flow chart in accordance with another embodiment of the invention for illustrating a method 1600 for online analyzing and determining similarity of a known logo with any logo detected in and analyzed from the Internet 112 .
- the web crawler 284 itself possesses the capabilities of doing its own object analysis by having its own object analyzer (i.e., object analyzer 1008 ).
- Step 1620 receives known logo 1610 as input logo-to-search. Stated alternatively, a determination is to be made if known logo 1610 is being used on the Internet 112 ; more specifically, if the Internet 112 contains a logo (which could exist in storage device 1005 a ) that is confusingly similar to the known logo 1610 .
- step 1610 From input step 1620 , logo 1610 is duplicated and stored by step 1630 in storing step 1005 (i.e., logo storage device 1005 a ).
- step 1640 executes method 1008 of FIG. 14 (i.e., web crawler 284 with the object analyzing process 1008 ) to determine if any logos on the Internet 112 are confusingly similar to the known logo 1620 .
- Step 1640 uses the object analyzer 1001 to analyze all objects discovered on the Internet 112 by the web crawler 284 .
- Method step 1640 may be distributed on hundreds of parallel computers.
- step 1560 displays the results, along with displaying for the similar logos the corresponding metadata and URL from storage device 1003 and database storage 260 for URLs, respectively.
- Web crawler 284 was activated to scan the Internet 112 and sweep servers 108 , to search for web objects including images, by automatically following hyperlinks contained in web site elements 113 .
- the web crawler 284 received an URL from storage device 100 a .
- the received URL pointed to a web site with the following content which was written in typical HTML language:
- the foregoing web site contained two important elements.
- the first important element was an image (i.e., both the word(s) and the design(s)/logo(s) in a mark) defined by ⁇ img . . . >.
- the URL of this image was stored in data storage device 260 .
- the following information on the image was stored in the object storage device 248 :
- a search for the “adidas” logo or design was conducted for all objects including images (i.e., both text or words and designs in a mark) contained in the object storage device 248 .
- the system received the “adidas” logo using the source code ( . . . ).
- the system created unique identifier “10001” (see FIG. 18 ) for the entered “adidas” logo and stored the “adidas” logo in storage device 1005 a .
- object analysis method 1007 was executed for analyzing the content of objects in object storage device 248 .
- a matrix of numbers were produced for each object from pixels in each object. Each pixel consists of three (3) numbers representing the colors red, green, and blue. The matrix of numbers were created or computed in RAM 270 when the object(s) were loaded from storage.
- RAM 270 created for image with “id 970729” a matrix of numbers comprising:
- FS_SearchLogo(Image,Logi[i], LogoInfo) was a computer vision algorithm that searched for the “adidas” logo with id 10001 inside the image with “id 970729” by comparing a mathematical template for the “adidas” logo with id 10001 with the matrix of numbers for image with “id 970729.”
- the computer vision algorithm used for this application was called “Template Matching”.
- the variable “LogoInfo” held the results of the analysis, storing information about the region where the “adidas” logo with id 10001 was found in image with “id 970729”, and the similarity of that particular region with the searched “adidas” logo.
- the “FS_SearchLogo” function created the mathematical model template automatically when the first search for a logo was executed (on demand).
- the algorithm used for creating the mathematical model was “Create Template”. In this Example II the search was for “adidas” logo with id 10001.
- the template matching algorithms required a template for the “adidas” logo which was automatically generated from the known “adidas” logo.
- the Mathematical Model Template for the known “adidas” logo 10001 comprised:
- Threshold 423434 0 0 0 0.5 1 0 0 0 0 0.5 2 2 0.5 0 0 0.5 2 1.5 1.5 2 0 0.5 2 1.5 1.5 1.5 2 1 2 1.5 1.5 1.5 1.5 1.5 1.5 1.5 2 2 2 2 2 2 2 0 0 0 0 0 0 0 0 0 0 0 0
- the decision whether the template was contained in a particular region of the image with “id 970729” was made by using a “score” (i.e., the degree of similarity) that expressed how good the template matched a region of the image. If the score was above a desired threshold represented by “Threshold 423434” (e.g. 60%), the process assumed the “adidas” logo with id 10001 was found. Thus, embodiments of the present invention provide determining the region of the object (e.g., image with “id 970729”) where the known object (e.g., “adidas” logo or design with id 10001) is located.
- a “score” i.e., the degree of similarity
- the function for storing the metadata in object metadata device 1003 also retrieved the next image to process from object storage device 248 (see FIG. 10 ) to begin or repeat the method again.
- Embodiments of the present inventions also broadly provide speedy data gathering of possible trademark infringement or dilution cases, including providing URL's of suspect sites for tracking or enforcement purposes and showing areas of potential brand erosion in Internet commerce.
- Embodiments of the present inventions provide a system to search images (e.g., both text or words and designs or logos in marks) in the Worldwide Internet by specifying the visual image content in means of: text contained in any images; logos or designs contained in any images; faces of people contained in any images including face recognition; and two (2) dimensional objects like animals, cars, etc. contained in any images.
- Embodiments of the present inventions search a database for images which are substantially identical or similar to any known images.
- Embodiments of the present inventions also enable people to search the Internet for images that have a specified visual content.
Abstract
A method and system for discovering from a database an object which is confusingly similar with a known object. A database, such as the internet, is searched for objects which, when discovered, may be duplicated and stored. A determination is then made if any object from the database is confusingly similar with a known object. A computer-readable storage medium storing program for causing a processing system to perform the steps of duplicating objects from a database to produce duplicated objects; storing the duplicated produce to produce stored duplicated objects; and determining if any stored duplicated object is confusingly similar with a known object.
Description
- This patent application is a continuation of pending application Ser. No. 11/585,668 filed Oct. 24, 2006 by Rene Seeber, which is a continuation of U.S. Pat. No. 7,130,466, filed Dec. 21, 2000, and issued Oct. 31, 2006.
- 1. Field of the Invention
- This invention relates generally to computer networks. More particularly, this invention provides for a system and method for searching and compiling from a database, such as the Worldwide Internet, images that have a specified visual content, and for determining if any of the compiled images are substantially similar to one or more known images.
- 2. Description of the Background Art
- In its embryonic stage the Worldwide Internet provided a research-oriented environment where users and hosts were interested in a free and open exchange of information, and where users and hosts mutually trusted one another. However, the Internet has grown dramatically, currently interconnecting over 100,000 computer networks and several million users. Because of its size and openness, the Internet has become a target of trademark and service mark infringement or misuse. Virtually every trademark or service mark is available for unauthorized use on the Internet. Before connecting, companies balance the rewards of an Internet connection against risks of infringement of trademarks and servicemarks.
- An entity's brands, trademarks, or servicemarks may be its most valuable asset. This is especially true with global intellectual property such as brands, trademarks, or servicemarks where integrity of the brand, trademark or servicemark is vital in new markets. Unfortunately, piracy of such intellectual property in many of these markets already costs leading corporations billions of dollars in lost sales annually, including new forms of piracy on the Worldwide Internet. Brand images (or look-alike marks) can be surreptitiously posted on web pages for selling fraudulent or unauthorized goods to a global market. If the presence of any brand, trademark or servicemark on the Internet becomes compromised, the result can be dilution of such any brand, trademark or servicemark, and ultimate loss of market share.
- In the Worldwide Internet the number of web sites and the number of images increases daily by millions. Right now, there are expected to be more than 500 million images in the Internet. While searching for regular text in the Internet is known (e.g., commercial text search engines like Yahoo, Altavista, Lycos, etc.), searching solely for images is much more difficult. Presently, searching for images in the Internet is possible only by looking at an image name, e.g., “Clinton.gif,” or by looking at the text grouped around an image in a website (e.g., commercial sites like “richmedia.lycos.com,” Altavista image finder, etc.). It is believed that there is presently no feasible system to efficiently search for images in the Internet by specifying their visual content, because no computer system or computer method is presently available to detect the specified visual content of an image from all of the millions of images provided in the Internet.
- Therefore, what is needed and what has been invented is a system and method for searching and compiling from a database, such as the Worldwide Internet, images that have a specified visual content, and for determining if any of the compiled images are substantially similar to one or more known images. What has been more specifically invented is a high-precision, automated visual detection service to protect global trademarks, servicemarks, and brands from infringement, dilution, or tarnishment by look-alike or imposter marks and brands on the Internet. The visual detection technology provided by the present invention finds a brand, trademark, or servicemark on Internet web pages, and also finds designs, symbols, shapes, and signs that closely resemble the brand, trademark or servicemark. The present invention also identifies logos within a larger picture and text within images.
- The present invention broadly provides a system and method for searching and discovering from a database (e.g., the Worldwide Internet) an object (e.g. a logo, a trademark, etc.) which is confusingly similar with a known object. Broadly, an object crawler sweeps websites of the Internet by automatically following hyperlinks contained in the websites. On each website the object crawler identifies all objects and duplicates them by downloading them on servers of a temporary storage system. Broadly further, after the object are downloaded by the object crawler and stored on the servers of the temporary storage system, the visual content of the objects may be analyzed, such as by hundreds of parallel computers analyzing object content. This may be done in a massive parallel manner with hundreds of computers (e.g., three hundred computers or more). Each computer object operates an object analysis software component which processes one or more input objects and produces as output descriptive information in terms of text and numbers about what content is in the object(s). For each object the following information may be produced and stored: object size; “fingerprint” for efficient identification of substantial similar objects; all text contained in the object(s); “fingerprint” of each face contained in the object(s); information about the logos/trademarks contained in the object(s); and information about things and images contained in the object(s).
- In one embodiment of the present invention, a graphical user interface is provided where the user may enter search criteria for the object to be searched. The search criteria to be entered in the graphical user interface may include one or more of the following search criteria: (i) one or more text strings that may be contained in the object including any image; (ii) one or more logo, trademarks or servicemarks selected from a list of predefined logos, trademarks or servicemarks that may be contained in the object including any image; (iii) one or more things or physical features or shapes selected from a list of predefined logos, trademarks or servicemarks that may be contained in the object including any image; (iv) one or more faces of facial templates that may be contained in the object including any image; and (v) one or more images that look substantially similar.
- In another embodiment of the present invention, a system and method is provided for searching for an entity's logos, trademarks or servicemarks in objects and images in the Worldwide Internet. A known logo and/or trademark and/or servicemark is provided and is entered into the system of the present inventions; and the content of each object in the internet is compared with the known logo and/or trademark and/or servicemark to determine if there is any confusing similarity. If a confusingly similar logo and/or trademark and/or servicemark appears in the internet object, a reference to the internet object is stored as search results. After scrutinizing objects in the internet, the user may access the search results.
- In yet another embodiment of the present invention, a system and method is provided for searching for faces of people or animals that are substantial identical to a known face. The system and method of embodiments of the present invention accept as input an object (e.g., a scanned photograph) that contains at least one face. Subsequently, the input face is compared with all faces in the internet objects (including images) using already computed face “fingerprints” available in storage. The result of the comparison is output in the form of a list of substantial identical objects (including images) that contain a face that is similar or substantially identical to the input face.
- Embodiments of the present invention more specifically provide a method for discovering from a database (e.g., the Worldwide Internet) an object which is confusingly similar with a known object comprising: (a) searching (e.g. searching with a web crawler by following hyperlinks contained in web site elements) a database for objects; (b) providing a known object; and (c) determining if any object from the database is confusingly similar with the known object. The method preferably additionally comprises duplicating the objects from the database to produce duplicated objects; storing the duplicated objects to produce stored duplicated objects; and determining if any stored duplicated object is confusingly similar with the known object. The method further preferably additionally comprises determining the degree of similarity of any stored duplicated object with the known object. The objects may be selected from the group consisting of graphic images, videos, audio sounds and mixtures thereof. Each of the objects may be an intellectual property selected from the group consisting of logos, trademarks, service marks, and mixtures thereof. Determining if any object is confusingly similar with the known object further preferably comprises determining if all of the necessary metadata is available for any of the stored duplicated objects; and if not, the necessary metadata is developed for the stored duplicated objects. Determining if any object is confusingly similar with the known object further preferably comprises performing one or more of the following process steps: conducting an optical character recognition analysis on the object; conducting a facial analysis on the object; conducting a watermark analysis on the object; conducting a signature analysis on the object; and conducting an object similarity analysis on the object.
- Embodiments of the present invention also more specifically provide a method comprising accessing a store that is storing duplicated objects from a database (e.g., an Internet database); and determining if any of the duplicated objects stored in the store are similar with a known object.
- Embodiments of the present invention further also more specifically provide a computer-readable storage medium storing program code for causing a processing system to perform the steps of: searching a database for objects; duplicating the objects from the database to produce duplicated objects; storing (e.g., maintaining in memory or transferring into memory) the duplicated objects to produce stored duplicated objects; determining if any stored duplicated object is confusingly similar with a known object.
- Embodiments of the present invention also provide for a system for discovering from a database an object which is confusingly similar with a known object comprising: a search engine for searching a database for objects; a duplicator coupled to the search engine for duplicating objects from the database to produce duplicated objects; a store coupled to the duplicator for storing the duplicated objects to produce stored duplicated objects; and determining means, coupled to the store, for determining if any stored duplicated object is confusingly similar with a known object. The system additionally preferably comprises determining the degree of similarity of any stored duplicated object with the known object.
- The present invention further also provides a system for discovering from a database an object which is confusingly similar with a known object comprising: means for searching a database for objects; means for duplicating objects from the database to produce duplicated objects; means for storing the duplicated objects to produce stored duplicated objects; and means for determining if any stored duplicated object is confusingly similar with a known object. The system additionally preferably comprises means for determining the degree of similarity of any stored duplicated object with the known object.
- The present inventions also provides a method for determining a degree of similarity between a known object and an object duplicated from a database comprising: duplicating an object from a database to produce a duplicated object; analyzing the content of the duplicated object (e.g., by assigning numbers for each pixel in the duplicated object) to produce a matrix of numbers; producing a model template from a known object; and comparing the model template of the known object with the matrix of numbers to determine the degree of similarity between the duplicated object and the known object. The method for determining a degree of similarity between a known object and an object duplicated from a database preferably additionally comprises one or more of the following process steps: providing a threshold degree of similarity to set a standard for confusingly similarity between the known object and the duplicated object; displaying the degree of similarity if the degree of similarity is at least equal to the threshold degree of similarity; and determining what region of the object the known object is located. The matrix of numbers is created in a RAM when the object (or image) is loaded from storage. The model template is computed and/or created automatically when the first search for object (e.g., a logo) is executed. The model template may be stored in a RAM. Each pixel consists of three numbers representing red, green, and blue. Color depends on algorithms. For example, in object or image searching, the colored image is converted into a grayscale image; subsequently, the actual analysis (or object/image detection) is performed on the grayscale image. The foregoing provisions along with various ancillary provisions and features which will become apparent to those skilled in the art as the following description proceeds, are attained by the practice of the present invention, a preferred embodiment thereof shown with reference to the accompanying drawings, by way of example only, wherein:
-
FIG. 1 is a block diagram illustrating a user network access system in accordance with the present invention; -
FIG. 2 is a block diagram illustrating details of a company computer system; -
FIG. 3A is a schematic diagram of a web crawler coupled to the Internet and its associated servers and further coupled to an object analyzer and storage device; -
FIG. 3B is a schematic diagram of a web crawler coupled to the Internet and to an object analyzer and storage device; -
FIG. 4 is a block diagram of a RAM device including an operating system, a communication engine, and a browser; -
FIG. 5 is a block diagram for an embodiment of the web crawler; -
FIG. 6 is a block diagram for another embodiment of the web crawler; -
FIG. 7 is a block diagram for an embodiment of the object analyzer and storage device; -
FIG. 8 is a block diagram for another embodiment of the object analyzer and storage device; -
FIG. 9 is a flowchart in accordance with an embodiment of the invention broadly illustrating a method for sweeping or canvassing a database, such as the Worldwide Internet, for detecting, duplicating, and storing objects (e.g., images, videos, and audio sounds); -
FIG. 10 is a flowchart in accordance with an embodiment of the invention broadly illustrating a method for broadly analyzing objects stored after being duplicated from a database, such as the Worldwide Internet; -
FIG. 11 is a flowchart in accordance with an embodiment of the invention for illustrating a method for more specifically analyzing the stored objects fromFIG. 10 ; -
FIG. 12 is a flowchart in accordance with an embodiment of the invention for illustrating a method for analyzing an image after the stored object has been determined to be an image in accordance with the method schematically illustrated inFIG. 11 ; -
FIG. 13 is a flowchart in accordance with an embodiment of the invention for illustrating a method for analyzing and determining similarity of a known logo with one or more stored logos duplicated from a database, such as the Worldwide Internet; -
FIG. 14 is a flowchart in accordance with another embodiment of the invention broadly illustrating a method for online sweeping or canvassing a database for online detecting, analyzing, duplicating, and storing objects; -
FIG. 15 is a flowchart broadly illustrating a method for adding and storing URLs which are to be searched in a database; -
FIG. 16 is a flowchart in accordance with another embodiment of the invention for illustrating a method for online analyzing and determining similarity of a known logo with any logo detected and analyzed in a database, such as the Worldwide Internet; -
FIG. 17 is a pictorial of an image-object for Example I that was duplicated from the Internet and stored in the object storage device; and -
FIG. 18 is a pictorial of a known image that was used in Example II to determine if any of the images contained in object storage device were substantially similar to the known image. - The following description is provided to enable any person skilled in the art to make and use the invention, and is provided in the context of a particular application and its requirements. Various modifications to the embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles, features and teachings disclosed herein.
- Referring now to
FIG. 1 there is a seen a block diagram illustrating an exemplary user network access system, generally illustrated as 100, in accordance with various embodiments of the present invention.System 100 includes a company computer system, generally illustrated as 104, a plurality of servers, generally illustrated as 108, and an interconnected networks of computers (“Internet”) generally illustrated as 112, for coupling thecompany computer system 104 to the plurality ofservers 108 which include a plurality of web site elements, generally illustrated as 113. Theservers 108 may include any number of servers, such asservers web site elements 108 represent web site elements for eachserver web site elements 108 are typically coupled to a respective computer (not shown) via an internal network signal bus (not shown), and represents a respective possessor or owner of a web page system for advertisement, informational purposes, services, etc., on theInternet 112. Exemplary advertisement, informational purposes, and services include promotional services, sales information, biographical information, e-mail service programs, address book service programs, calendar service programs, paging service programs, and company database service programs, etc., all of which may include audio sounds, videos, and one or more graphic images (e.g., a reproduction or imitation of a design and text or words including a reproduction or imitation of a person, a thing, a mark, or a symbol) including logos (e.g. non-word elements, a design such as graphic designs, etc), trademarks (e.g., a word, symbol or device pointing distinctly to the origin or ownership of merchandise to which it is applied and legally reserved to the exclusive use of the owner as maker or seller), service marks (e.g. a mark or device used to identify a service offered to customers), faces of people, 2-dimensional objects like animals and cars, etc., all of which may be nonexclusively referred to as “objects.” Thus, “objects” comprise images, videos, audio sounds, and the like. If the user of thecompany computer system 104 wants to access one of the services of one of theservers 108, the user applies a known Uniform Resource Locator (URL) to access a web page operated by the possessor of server whose services are to be accessed. - Referring now to
FIG. 2 there is seen a block diagram illustrating details of thecompany computer system 104. Thecomputer system 104 includes a processor 210 (e.g., a Central Processing Unit) such as a Motorola Power PC®) microprocessor or an Intel Pentium® microprocessor. Aninput device 220, such as keyboard and mouse, and anoutput device 230, such as a Cathode Ray Tube (CRT) display, are coupled via asignal bus 240 toprocessor 210. Acommunications interface 250, adata storage device 260, such as Read Only Memory (ROM) or a magnetic disk, and a Random-Access Memory (RAM) 270 are further coupled viasignal bus 240 toprocessor 210. The communications interface 250 of thecomputer system 104 is coupled to theInternet 112 as shown in and described with reference toFIG. 1 . Thecomputer system 104 also includes anoperating system 280, aweb crawler 284, anobject storage device 248, analyzerparametric Rules 288 for determining similarity, object analyzer andstorage device 290, and adownloading engine 292. - Referring now to
FIG. 3A there is seen a schematic diagram of theweb crawler 284 coupled to the Internet 112 (including the servers 108), and to both thedata storage device 260 and theobject storage device 248 which latter both in turn are coupled to the object analyzer andstorage device 290. As schematically illustrated inFIG. 3A , theweb crawler 284 “walks through” theInternet 112 and sweeps theservers 108, searching for web objects including images, by automatically following hyperlinks contained in the respectiveweb site elements 113. It is to be understood that theweb crawler 284 may go to any web site, including specified web sites that are not linked (e.g., top level domains (TLD)). Theweb crawler 284 may also temporarily store URLs, hyperlinks, and copies of objects. An object transfer engine (identified below as “440” and “550”) may then respectively transfer the web objects and the URLs of the objects todata storage device 260 and to objectstorage device 248. Each object contains pixels (e.g. 10,000 or more pixels) and numbers are assigned to each pixel when the object is being analyzed by content. As will be explained below, there are two embodiments for theweb crawler 284. The object analyzer andstorage device 290 are coupled to a display oroutput device 320 and includes the analyzerparametric Rules 288 for determining similarity and the downloadingengine 292 for downloading the web objects and the URLs from thedata storage device 260 and theobject storage device 248, respectively. As will be also explained below, there are also two embodiments for the object analyzer andstorage device 290 wherein web objects may be analyzed and wherein descriptive information about the content of each web object may be stored. As previously indicated, object analyzer andstorage device 290 analyzes web objects by number of pixels in each web object and assigns numbers for each pixel and stores the numbers (i.e., the descriptive information about content of each object). Each pixel consists of three (3) numbers representing the colors red, green, and blue. InFIG. 3B theweb crawler 284 is coupled directly to the object analyzer andstorage device 290, instead of being coupled to the object analyzer andstorage device 290 viaobject storage device 248 anddata storage device 260. Theweb crawler 284 inFIG. 3B is also coupled to adisplay device 390. Image or object analysis components employed by theanalyzer 290 for each object include, but is not limited to, text (e.g. words and the like), logos, faces (e.g., both human and animal faces, and the like), and two dimensional objects or things (e.g., cars, planes, animals, and the like), and combinations thereof. - The
operating system 280 has a program for controlling processing byprocessor 210, and may be stored at any suitable location (e.g., in object storage device 260) and is loaded by the downloadingengine 282 intoRAM 270 for execution (seeFIGS. 2 and 4 ). As best shown inFIG. 4 ,operating system 280 includes or controls acommunication engine 282 for generating and transferring messages including objects to and from theInternet 112 via thecommunications interface 250.Operating system 280 further includes or controls an internet engine such as aweb browser 246, e.g., the Netscape™ web browser produced by Netscape, and the Internet Explorer™ web browser produced by the Microsoft Corporation. Theweb browser 246 may comprise an encryption or decryption engine (not shown in the drawings for encrypting or decrypting messages). Thebrowser 246 further receives web page data including web objects and/or other desired information. Theweb browser 246 enables a user of thecomputer system 104 to receive objects including images from theservers 108 via theInternet 112. - One skilled in the art will recognize that the
system 100 may also include additional information, such as network connections, additional memory, additional processors, Local Area Networks (LANs), input/output lines for transferring information across a hardware channel, theInternet 112 or an intranet, etc. One skilled in the art will also recognize that the programs and data may be received by and stored in the system in alternative ways. For example, a computer-readable storage medium (CRSM) reader such as a magnetic disk drive, hard disk drive, magneto-optical reader, CPU, etc. may be coupled to thesignal bus 240 for reading a computer-readable storage medium (CRSM) such as a magnetic disk, a hard disk, a magneto-optical disk, RAM, etc. Accordingly, thesystem 100 may receive programs and data via a CRSM reader. Further, it will be appreciated that the term “memory” herein is intended to cover all data storage media whether permanent or temporary. Therefore, it will be apparent to those skilled in the art that several variations of the system elements are contemplated as being within the intended scope of the present invention. For example, given processor and computer performance variations and ongoing technological advancements, hardware elements (e.g., multiplexers, etc.) may be embodied in software or in a combination of hardware and software. Similarly, software elements may be embodied in hardware or in a combination of hardware and software. Further, while connection to other computing devices may take place atoutput device 230 orcommunications interface 250, wired, wireless, modem and/or connection or connections to other computing devices (including but not limited to local area networks, wide area networks and the Internet 112) might be utilized. A further example is that the use of distributed processing, multiple site viewing, information forwarding, collaboration, remote information retrieval and merging, and related capabilities are each contemplated. Various operating systems and data processing systems can also be utilized, however at least a conventional multitasking operating system such as Windows95® or Windows NT® (trademarks of Microsoft, Inc.) running on an IBM® (trademark to International Business Machines, Inc.) compatible computer is preferred and will be presumed for the discussion herein.Input device 220 can comprise any number of devices and/or device types for inputting commands and/or data, including but not limited to a keyboard, mouse, and/or speech recognition. - The
web crawler 284 of the present invention sweeps or “walks through” theInternet 112 includingservers 108 by automatically following hyperlinks contained in the respectiveweb site elements 113, or by going to specific web sites that are not linked, such as top level domains (TLD). Theweb crawler 284 on each web site identifies all web objects and duplicates or copies them from theservers 108 andInternet 112.FIGS. 5 and 6 represent two respective embodiments for theweb crawler 284. Referring toFIG. 5 , there is seen one embodiment of theweb crawler 284 as includingcrawler Rules 406 for determining or identifying web objects on the web, anobject search engine 410 for searching all of theservers 108 for web objects in accordance with the crawler Rules 406, aURL storage device 420 for storing Uniform Resource Locators for each of the web sites, and anobject storage device 430 for receiving and temporarily storing web objects that have been identified by theweb crawler 284 in accordance with the crawler Rules 406. Theweb crawler 246 ofFIG. 5 may also include anobject transfer engine 440 for transferring the stored web objects from theobject storage device 430 to an object data base, such as webobject storage device 248, as well as aURL transfer engine 450 for transferring Uniform Resource Locators fromURL storage device 420 to a URL data base, such asdata storage device 260. Theweb crawler 284 ofFIG. 5 continually monitors theentire Internet 112 including theservers 108 for any and all web objects. Thus, this embodiment of theweb crawler 284 continually scavenges theInternet 112 including theservers 108 coupled thereto for any and all web objects without making any discernment as to substantial similarity between any object on theInternet 112 and/orservers 108 and any known object. - Referring now to
FIG. 6 , there is seen another embodiment of theweb crawler 284. This embodiment of theweb crawler 284 includes aURL storage device 510 for storing Uniform Resource Locators for each of the web sites, and an object-to-be-searched storage device 520 which receives and stores web objects that are to be searched on theInternet 112 andservers 108 by theweb crawler 284. The user of this embodiment of theweb crawler 284 enters or inputs the desired known objects into the object-to-be searchedstorage device 520 whose substantially similarity is to be searched for on theInternet 112 andservers 108. This embodiment of theweb crawler 284 also includescrawler Rules 526 for determining substantial similarity between the known object(s) stored in the object-to-be searchedstorage device 520 and any web objects discovered on theInternet 112 and/orservers 108. Theweb crawler 284 ofFIG. 6 further also includes an object search andcomparison engine 530, an objects-copied-from-web storage device 540, anobject transfer engine 550 and aURL transfer engine 560. The object search andcomparison engine 530 searches in accordance withcrawler Rules 526, theInternet 112 andservers 108 for known objects that are stored in the object-to-be-searched storage device 520. Theengine 530 also compares in accordance with the crawler Rules 526 each web object found on theInternet 112 and/orservers 108 with each known object stored in the object-to-be-searched storage device 520; and if there is a substantial similarity in accordance with the crawler Rules 526, theengine 530 downloads (i.e., duplicates or copies) the substantially similar web object(s) off of theInternet 112 andservers 108 into the objects-copied-from-web storage device 540. Theobject transfer engine 550 duplicates and transfers the substantially similar web object(s) from the objects-copied-from-web storage device 540 to a data base, such asobject storage device 248. TheURL transfer engine 450 transfers Uniform Resource Locators fromURL storage device 510 to a URL data base, such asdata storage device 260. Theweb crawler 284 ofFIG. 6 selectively searches theInternet 112 including theservers 108 for any web objects that are substantially similar to the known object(s) stored in the object-to-be-searched storage device 520. Thus, for this embodiment of the invention including theweb crawler 284, theweb crawler 284 scavenges theInternet 112 and theservers 108 with discernment, looking for any and all web objects that are substantially similar to any and all known objects stored in the object-to-be-searched storage device 520. - Referring in detail now to
FIG. 7 andFIG. 8 , there is seen two respective embodiments for the object analyzer andstorage device 290. Referring now toFIG. 7 , there is seen one embodiment of the object analyzer andstorage device 290 as including the analyzerparametric Rules 288 for determining similarity, an analyzerobject comparison engine 730, the downloadingengine 292, and a descriptiveinformation storage device 710. The descriptiveinformation storage device 710 contains descriptive information (i.e., mathematical model templates) about one or more known objects for making a determination if the known objects are substantially similar to any of the web objects that were duplicated or copied from theInternet 112 orservers 108 by theweb crawler 284. The analyzerparametric Rules 288 for determining similarity are the rules and parameters that the object analyzer andstorage device 290 employs to determine if there is substantial similarity between the descriptive information pertaining to the known objects stored in the descriptiveinformation storage device 710 and the web objects, more specifically the information on the web objects, which is stored in theobject storage device 248 after being removed or extracted from theInternet 112 and/orservers 108. The web-copied or web-duplicated web objects are subsequently either initially stored inobject storage device 430, or in the objects-copied-from-web storage device 540, or the web-copied web objects bypass these crawler storage sections and are loaded directly into theobject storage device 248. The downloading engine 297 is capable of downloading web objects (including associated descriptive information on web objects) and URLs fromobject storage device 248 anddata storage device 260, respectively, into the object analyzer andstorage device 290, more specifically into the analyzerobject storage device 720 of the object analyzer andstorage device 290 where the downloaded information is converted into a plurality of numbers from the number of pixels in each web object. As was previously indicated, each pixel in an object is given particular numbers producing a set of numbers which are compared with the mathematical model template of the known object for determining a degree of similarity. Each pixel consists of three (3) numbers representing the colors red, green, and blue. Alternatively, a separate downloading engine (not shown) is employed for downloading URLs from thedata storage device 260 into the analyzerobject storage device 720 of the object analyzer andstorage device 290. - Once the downloaded web objects and their associated descriptive information arrives in the
analyzer object device 720, the analyzerobject comparison engine 730, under the aegis of the analyzerparametric Rules 288 for determining similarity, makes a comparison between the downloaded web objects (including their associated descriptive information which is in the form of a matrix of numbers from pixels) and the descriptive information (i.e., a template such as a mathematical model template) concerning one or more known objects in the descriptiveinformation storage device 710. Depending on the degree of substantial similarity, which depends on the analyzerparametric Rules 288, a match is made between one or more of the downloaded web objects and one or more of the known objects. This information including the corresponding URL(s) for the downloaded web objects may then be provided or displayed through anysuitable output device 320, including a printer or video screen or any of the like. Based on the analyzerparametric Rules 288, or the analyzerparametric Rules 288 in combination with the analyzerobject comparison engine 730, the degree of similarity may also be provided or displayed. By way of example only, if one or more of the downloaded objects are 90% similar to one or more known objects, such 90% degree of similarity is also provided or displayed. Thus, the analyzerparametric Rules 288, or the analyzerparametric Rules 288 in combination with the analyzerobject comparison engine 730, enable the degree of similarity between downloaded web objects and known objects to be determined. Typical degree of similarity would be 100%, 95%, 90%, 85%, 80%, or any suitable degree of similarity that is desired. As was previously mentioned, the degree of similarity is preferably determined by comparing a mathematical model template of the known object with a matrix of numbers generated from the number of pixels in each web object, with each pixel consisting of three numbers representing the colors red, green, and blue. The manner in which color in an object or image is addressed depends on each algorithm. For example, in the logo search exemplified inFIG. 13 , a colored image is converted into a grayscale image; then the actual analysis/logo detection is performed on the grayscale image. The matrix of numbers is computed in a RAM, such asRAM 270, when the object or image is loaded from storage, such asstorage device 248. - Referring now to
FIG. 8 , there is seen another embodiment of the object analyzer andstorage device 290 as including analyzerobject comparison engine 830, and an (optional) analyzerparametric Rules 840, preferably for “fine tuning” or tweaking any determination of similarity made by theweb crawler 284, more specifically theweb crawler 284 ofFIG. 6 . The analyzerparametric Rules 840 may be optional in the sense that analyzerparametric Rules 840 may not be needed if the crawler Rules 526, or if the crawler Rules 526 in combination with the object search andcomparison engine 530, are sufficient enough such that the web objects stored in the objects-copied-from-web storage device 540 has the desired degree of similarity with the known objects stored in the object-to-be-searched storage device 520. In such a case the web-copied or web-duplicated web objects may be displayed through the output or display device 390 (seeFIG. 3B ), such as any suitable printer and/or video screen or the like. The crawler Rules 526, or the crawler Rules 526 in combination with thecomparison engine 530, like the analyzerparametric Rules 288 or the analyzerparametric Rules 288 in combination with the analyzerobject comparison engine 830, may also furnish the degree of similarity between web objects in the objects-copied-from-web storage device 540 and the known objects in the objects-to-be-searched storage device 520. If the crawler Rules 526, or if the crawler Rules 526 in combination with the object search andcomparison engine 530, are not sufficient for providing a desired degree of similarity (e.g., 100% or 95% degree of similarity), then the analyzerparametric Rules 840, or the analyzerparametric Rules 840 in combination with thecomparison engine 830, would be employed for “fine tuning” or tweaking the determination of similarity determined by thecrawler 284 ofFIG. 6 , more specifically by the crawler Rules 526, or by the crawler Rules 526 in combination with the object search andcomparison engine 530, ofFIG. 6 . Thus, if the degree of similarity detected by thecrawler 284 ofFIG. 6 is say 50%, then the object analyzer andstorage device 290 ofFIG. 8 , may be used to “fine tune” or tweak this 50% degree of similarity to produce a more sufficient degree of similarity. More specifically, the analyzerparametric Rules 840, or the analyzerparametric Rules 840 and thecomparison engine 830 in combination with the information contained in the descriptiveinformation storage device 710, for the object analyzer andstorage device 290 ofFIG. 8 would be employed to produce a higher degree of similarity (e.g., 90%) between the web object(s) and the known object(s). - The object analyzer and
storage device 290 ofFIG. 8 may also (optionally) include the downloadingengine 292. If the embodiment of the invention inFIG. 3B is employed such that theweb crawler 284 is coupled directly to the object analyzer andstorage device 290, instead of being coupled viaobject storage device 248 anddata storage device 260, the downloadingengine 292 would not be necessary as theobject transfer engine 550 of the web crawler could directly transfer any web objects recovered from theInternet 112 and theservers 108 to the analyzerobject storage device 820. The object analyzer andstorage device 290 ofFIG. 8 also has the descriptiveinformation storage device 710 and an analyzerobject storage device 820 which functions comparably to the analyzerobject storage device 720. - Referring now to
FIG. 9 , there is seen a flowchart for broadly illustrating amethod 900 for sweeping or canvassing a database, such asInternet 112.Storage steps 1000 stores with priorities all URLs whose associated web pages are to be searched byweb crawler 284. Step 910 removes fromstorage device 1000 a an URL with the highest priority. After removal of the highest priority URL, theweb crawler 284 finds the highest priority URL in theInternet 112 and searches for a web page associated with the highest priority URL. If theweb crawler 284 instep 920 determines that there is no web page associated with the highest priority URL, then the second highest priority URL is removed fromstorage device 1000 a and theweb crawler 284 repeats the determiningstep 920 for the second highest priority URL; that is, theweb crawler 284 finds the second highest priority URL in theInternet 112 and searches for a web page associated with the second highest priority URL. If theweb crawler 284 instep 920 determines that there is no web page associated with the second highest priority URL, the procedure is repeated for a third highest priority URL instorage device 1000 a, and so forth. Alternatively, theweb crawler 284 instep 920 determines if there are any more URLs instorage device 1000 a to be searched. In other words, isstorage device 1000 a empty of URLs to be searched? - Once it is determined in determining
step 920 that a web site orweb page 930 is associated with any particular URL, theweb page 930 is copied and downloaded bystep 940 intoweb crawler 284. After downloading bystep 940, all features or elements of the web site orweb page 930 are analyzed in analyzingstep 950 in accordance withcrawler Rules 406 for determining objects in the downloaded web site orweb page 930. An element of a web site orweb page 930 is any hypertext mark-up language (HTML) element by definition. HTML is the standard procedure for writing a web site. Stated alternatively,web crawler 284 analyzes the downloaded web site orweb page 930 associated therewith for objects. Step 960 determines if any hyperlinks are discovered for any element; and, if so, the hyperlinks are stored by storage step 1000 (e.g., instorage device 1000 a). Stated alternatively further, theweb crawler 284 determines from its associated downloadedweb page 930 if any of the elements contained therein include hyperlinks associated therewith; and, if so, the hyperlinks are transferred or downloaded to the storing step 1000 (e.g., downloaded intostorage device 1000 a). Hyperlinks effectively execute a “Go To” address wherein the address is the URL associated with the hyperlink. If no hyperlinks are discovered in any particular element by determiningstep 960, then determiningstep 970 determines if the particular element in the downloaded web site orweb page 930 includes an object. If one or more objects are found in the particular element being tested, then the object(s) are transferred to objectstorage device 248. The URL associated with the object discovered in the particular element is transferred (e.g., is transferred by web crawler 284) todata storage device 260. Subsequently, determiningstep 980 determines if any more elements remain in the downloaded web site orweb page 930. Stated alternatively, theweb crawler 284 determines if the last element in the downloadedweb page 930 has been tested by determiningsteps steps web page 930 has been addressed by determiningsteps method 900 is repeated for the next highest priority URL from the storage step 1000 (i.e., fromstorage device 1000 a). - Referring now to
FIG. 10 , there is seen a flowchart for broadly illustrating amethod 1007 for broadly analyzing objects stored after being duplicated from a database, such as theInternet 112. Instep 1020, the first object to be analyzed for similarity with a known object is removed from theobject storage device 248. After removal, a determination is made by determiningstep 1030 if all of the necessary metadata (i.e., description information data that describes the object which is preferably a matrix of numbers, with numbers representing a pixel in any stored object) is available for the object. The metadata or a matrix of numbers generated from pixels for any particular stored object is inmetadata storage device 1003. Determining step 1030 (i.e., using a database query device) searchesmetadata storage device 1003 for metadata for any particular object. If the necessary metadata for the particular object is not available, then the object is analyzed instep 1001 to develop the necessary metadata. Preferably,object analyzer 1001 develops the necessary metadata by receiving the particular object as input and analyzing that particular object for content (i.e., for metadata content). When the object is a video, each frame of the video will be analyzed for metacontent. Thus, videos are handled as multiple images. Afterstep 1001 and the development of the necessary metadata, a storingstep 1040 stores the developed metadata. Preferably the developed metadata is stored inmetadata storage device 1003. Subsequently, the next object is removed bystep 1050 fromobject storage device 248 and the entire procedure is repeated for the next object. If determiningstep 1030 determines that sufficient metadata exists for any particular object, then steps 1001 and 1040 are bypassed and the next step isstep 1050 which is to determine if more objects exist for analyzing. More specifically, a determination is made instep 1050 ifobject storage device 248 contains more objects which are to be tested to determine if the necessary metadata is available for the particular object. If more objects are available to by analyzed, then step 1060 retrieves the next object fromstorage device 248 andsteps step 1050 determines that no more objects exist or are available for analysis. - Referring now to
FIG. 11 there is seen a flowchart for broadly illustrating themethod step 1001 for developing the necessary metadata for any particular object.Object 1109 to be analyzed is input, or otherwise provided, for determining in determiningstep 1110 if theobject 1109 is a video. Ifobject 1109 is not a video then theobject 1109 is investigated in determiningstep 1120 to determine if theobject 1109 is an image (e.g., both the texts or words and logos or designs of marks). If theobject 1109 is a video then step 1130 analyzes each frame of the video. For each frame in the video,step 1130 employsimage analyzer 1002 for analysis and recognition operations on each frame. The results of performing an image analysis and an image recognition operation on each frame of an object video is collected bystep 1140 and is transferred in the form of metadata tooutput step 1150 for storage in step 1040 (seeFIG. 10 ). - The
image analyzer 1002 is employed instep 1130 for analyzing each frame of a video after determiningstep 1110 determines that the object is a video, or theimage analyzer 1002 is employed in step 1160 (i.e., the image analyzing step 1160) afterstep 1120 determines that the object itself is an image, e.g., the combination of designs or logos and texts or words in a mark, or the combination of two or more of the following in a mark: texts, logos, facial features, watermarks, signature features, and similarity features. Theimage analyzer 1002 for embodiments of the present invention performs one or more of the following analyses: OCR (optical character recognition) analysis which recognizes text (e.g., one or more words) in the image; face analysis which detects human or animal faces by employing templates stored in a storage step (identified below as “1005”); watermarks analysis which detects and reads embedded watermarks; signature analysis which produces a “digital fingerprint” of the image by calculating one or more numbers, and is employed to identify similar images that have similar “digital fingerprints;” and image similarity analysis which computes one or more numbers that describe the visual similarity of the image to or vis-a-vis images stored in a storing step (identified below as “1006”). Each calculated number for signature analysis and for image similarity analysis represents an algorithmic output from a respective algorithm. The more algorithms employed in the signature analysis and in the image similarity analysis, the more algorithmic outputs are produced; and the more algorithmic outputs produced, the more accurate the respective analysis is. The algorithms adjust for size and orientation (e.g., vertical or horizontal) of the object or image. As shown inFIG. 11 , the results computed by and/or obtained by the image analyzing step 1160 (e.g., the image analyzer 1002), along with the results collected by collectingstep 1140 ofstep 1130 are transferred to storingstep 1150 were object metadata is stored. - Referring now to
FIG. 12 , there is seen a flow chart in accordance with an embodiment of the invention for illustratingmethod 1002 for analyzing an image afterstep 1120 determines that the object is an image, or for analyzing an image in any frame of a video in accordance withstep 1130.Input step 1210 inputs the image to commence one or more of the following analyzing steps:OCR analyzing step 1220, face analyzingstep 1230,logo analyzing step 1240,watermarks analyzing step 1250,signature analyzing step 1260, and imagesimilarity analyzing step 1270. Analyzerparametric Rules 288 are stored (e.g., storage device 288 a stores analyzer parametric Rules 288).Rules 288 enable the production of image metadata by communicating with and transferring tosteps OCR analyzing step 1220 receives the pertinent algorithms from analyzerparametric Rules 288 for producing a plurality of numbers (i.e., OCR algorithmic outputs). For example, one algorithm received from analyzerparametric Rules 288 may be “Caere OCR” which may be purchased commercially from Caere Corporation of Los Gatos, Calif. As previously indicated, the analyzing steps employ algorithms which adjust for size and orientation of objects or images. - After the
OCR analyzing step 1220 has been performed on an image, theface analyzing step 1230 is conducted on the image by receiving the relevant algorithms from analyzerparametric Rules 288 to enablestep 1230 is produce the algorithmic outputs (i.e., numbers) for describing any face. For example, one algorithm received from analyzerparametric Rules 288 for analyzing a face may be “Face-It” which may be purchased commercially from Caere Corporation of Los Gatos, Calif. The more algorithms employed to produce numbers for describing a face, the more accurate theface analysis step 1230 will be. Facial templates (e.g., faces to be searched for on Internet 112) are stored at storing step 1004 (e.g., instorage device 1004 a). After theface analysis step 1230 has been conducted on an image, thelogo analysis step 1240 is conducted on the image. Logo templates (e.g., logos to be searched for on the Internet 112) are stored at storing step 1005 (e.g., instorage device 1005 a).Logo analysis step 1240 analyses any logos (e.g. design(s) or symbol(s) in a mark) within the image versus the logo templates instorage device 1005 a. A logo template fromstorage device 1005 a is superimposed over any logo in the image and is similarly produced by template matching. - A watermark analysis may subsequently be conducted on the image by the
watermarks analysis step 1250 which receives the relevant algorithms and other parameters from analyzerparametric Rules 288 for detecting and reading embedded watermarks in the image. For example, an algorithm used in thewatermarks analysis step 1250 is Digimark Watermarking which is commercially available from Digimark Corporation of Portland Oreg. - After the
watermarks analysis step 1250 has been conducted on the image to recognize and analyze the image for watermarks, asignature analysis step 1260 and animage similarity step 1270 is performed on the image. Thesignature analysis step 1260 receives the pertinent and relevant algorithms from the analyzerparametric Rules 288 and inputs into the algorithms detected variables, such as “color count” and “color distribution” to calculate one or more numbers to produce a “digital fingerprint” which are employed to identify images (i.e., known similar images) that have similar “digital fingerprints.” The imagesimilarity analysis step 1270 receives the pertinent, relevant algorithms for computing one or more numbers (e.g., algorithmic output(s) such as “Color-Histogram-Matching”) that describe the visual similarity if any to images in storingstep 1006. - Referring now to
FIG. 13 , there is seen a flowchart in accordance with an embodiment of the invention for illustrating amethod 1300 for analyzing and determining similarity of a knownlogo 1310 with one or more stored logos which are stored inobject storage device 248 after being duplicated from a database, such as theInternet 112.Step 1320 receives knownlogo 1310 as input logo-to-search. Stated alternatively, a determination is to be made if knownlogo 1310 is being used on theInternet 112; more specifically, if theInternet 112 contains a logo (which could exist instorage device 1005 a) that is confusingly similar to the knownlogo 1310. Frominput step 1320,logo 1310 is duplicated and stored bystep 1330 in storing step 1005 (i.e.,logo storage device 1005 a). After duplicating and storinglogo 1310 bystep 1330,step 1340 executesmethod 1007 ofFIG. 10 (i.e., the object analyzing process 1007) to determine if any logos stored inobject storage device 248 are confusingly similar to the knownlogo 1310.Step 1340 uses theobject analyzer 1001 to analyze all objects stored inobject storage device 248.Method step 1340 may be distributed on hundreds of parallel computers. Afterstep 1340 has executedobject analysis process 1007,step 1350 displays the results, along with displaying for the similar logos the corresponding metadata and URL fromstorage device 1003 anddatabase storage 260 for URLs, respectively. - Referring now to
FIG. 14 , there is seen a flow chart for broadly illustrating a method 1400 for online sweeping or canvassing a database, such asinternet 112, for online detecting, analyzing, duplicating, and storing objects. For this embodiment of the invention, theweb crawler 284 includes its own object analyzer.Storage step 1000 stores with priorities all URLs whose associated web pages are to be searched byweb crawler 284.Step 1410 removes fromstorage 1000 a an URL with the highest priority. After removal of the highest priority URL, theweb crawler 284 finds the highest priority URL in theInternet 112 and searches for a web page associated with the highest priority URL. If theweb crawler 284 instep 1420 determines that there is no web page associated with the highest priority URL, then the second highest priority URL is removed fromstorage 1000 a and theweb crawler 284 repeats the determiningstep 1420 for the second highest priority URL; that is, theweb crawler 284 finds the second highest priority URL in theInternet 112 and searches for a web page associated with the second highest priority URL. If theweb crawler 284 instep 1420 determines that there is no web page associated with the second highest priority URL, the procedure is repeated for a third highest priority URL instorage 1000 a. - Once it is determined in determining
step 1420 that a web site orweb page 1430 is associated with any particular URL, theweb page 1430 is copied and downloaded bystep 1440 intoweb crawler 284. After downloading bystep 1440, all features or elements of the web site orweb page 1430 are analyzed in analyzingstep 1450 in accordance withcrawler Rules 406 for determining objects in the downloaded web site orweb page 1430. As previously indicated, an element of a web site orweb page 1430 is a defined HTML element. Stated alternatively, theweb crawler 284 includes its own object analyzer for performing analyzes of the downloaded web site orweb page 1430 for objects associated therewith.Step 1460 ofstep 1450 determines if any hyperlinks are discovered for any element, and if so, the hyperlinks are stored by storage step 1000 (e.g., instorage device 1000 a). Stated alternatively,step 1460 ofstep 1450 of theweb crawler 284 determines from associated downloadedweb page 930 if any of the elements contained therein include hyperlinks associated therewith; and if so, the hyperlinks are transferred or downloaded to the storing step 1000 (e.g., downloaded intostorage device 1000 a). As previously indicated, hyperlinks effectively execute a “Go To” address wherein the address is the URL associated with the hyperlinks. If no hyperlinks are discovered in any particular element by determiningstep 1460, then determiningstep 1470 determines if the particular element in the downloaded web site orweb page 1430 includes an object (e.g., an image, an audio, or video). If one or more objects are found in the particular element being tested, then step 1001 (i.e.,method 1001 ofFIG. 11 ) is executed for the one or more objects.Step 1480 transfers and/or causes the results to be stored in objectmetadata storage device 1003. Subsequently,step 1485 determines if any more URLs exist in storage step 1000 (i.e.,storage device 1000 a) having a second highest priority. Stated alternatively,step 1485 tests to determine ifstorage device 1000 a is empty (i.e., have all URLs been removed for analyzing their associated web pages for objects?). If more URLs exist instorage device 1000 a, then step 1490 retrieves the next highest priority URL fromstorage device 1000 a and steps 1440 and 1450 are repeated for the next highest priority URL from the storing step 1000 (i.e., fromstorage device 1000 a). - Referring now to
FIG. 15 , there is seen a flow chart for broadly illustrating amethod 1500 for adding and storing URLs which are to be searched on theInternet 112. A new URL is received as input instep 1510, and then step 1520 transfers and/or otherwise causes the new URL to be stored in the storing step 1000 (i.e., instorage device 1000 a). The first new URL being stored instorage device 1000 a has the highest priority, followed by the second new URL which has the next highest priority, and so forth. - In
FIG. 16 there is seen a flow chart in accordance with another embodiment of the invention for illustrating amethod 1600 for online analyzing and determining similarity of a known logo with any logo detected in and analyzed from theInternet 112. For this embodiment of the invention, theweb crawler 284 itself possesses the capabilities of doing its own object analysis by having its own object analyzer (i.e., object analyzer 1008).Step 1620 receives knownlogo 1610 as input logo-to-search. Stated alternatively, a determination is to be made if knownlogo 1610 is being used on theInternet 112; more specifically, if theInternet 112 contains a logo (which could exist instorage device 1005 a) that is confusingly similar to the knownlogo 1610. Frominput step 1620,logo 1610 is duplicated and stored bystep 1630 in storing step 1005 (i.e.,logo storage device 1005 a). After duplicating and storinglogo 1610 bystep 1630,step 1640 executesmethod 1008 ofFIG. 14 (i.e.,web crawler 284 with the object analyzing process 1008) to determine if any logos on theInternet 112 are confusingly similar to the knownlogo 1620.Step 1640 uses theobject analyzer 1001 to analyze all objects discovered on theInternet 112 by theweb crawler 284.Method step 1640 may be distributed on hundreds of parallel computers. Afterstep 1640 has executedobject analysis process 1008, step 1560 displays the results, along with displaying for the similar logos the corresponding metadata and URL fromstorage device 1003 anddatabase storage 260 for URLs, respectively. - The invention will now be illustrated by the following set forth examples which are being given by way of illustration only and not by way of any limitation. All parameters such as, source code, model templates and ID numbers, etc., submitted in these examples are not to be construed to unduly limit the scope of the invention.
-
Web crawler 284 was activated to scan theInternet 112 and sweepservers 108, to search for web objects including images, by automatically following hyperlinks contained inweb site elements 113. Theweb crawler 284 received an URL from storage device 100 a. The received URL pointed to a web site with the following content which was written in typical HTML language: -
<html> <head> <title>Demonstration</title> <body> <p> Demonstration </p> </div> <img width=300 height=250 src=“./tshirt.jpb”></p> </div> <a href=“http://www.cobion.com”>http://www.cobion.com</a> </body> </html> - The foregoing web site contained two important elements. The first important element was an image (i.e., both the word(s) and the design(s)/logo(s) in a mark) defined by <img . . . >. The URL of this image was stored in
data storage device 260. The following information on the image was stored in the object storage device 248: -
- a unique image id, for example “970729” (see
FIG. 17 ) - width and height of the image, where width was equal to 300 pixels and height was equal to 250 pixels
- current date, for example 12/01/2000
- image-name, for example “tshirt.jpg”
- a unique image id, for example “970729” (see
- The second important element in the web site was a hyperlink defined by “<a href= . . . >.” This hyperlink pointed to the web site “http://www.cobion.com” and was stored in
storage device 1000. The stored information associated with this hyperlink was available for use to determine if the stored information including the image was confusingly similar with a known object. - A search for the “adidas” logo or design (i.e., the known object) was conducted for all objects including images (i.e., both text or words and designs in a mark) contained in the
object storage device 248. The system received the “adidas” logo using the source code ( . . . ). For later identification and reference, the system created unique identifier “10001” (seeFIG. 18 ) for the entered “adidas” logo and stored the “adidas” logo instorage device 1005 a. Subsequently, object analysis method 1007 (seeFIG. 10 ) was executed for analyzing the content of objects inobject storage device 248. A matrix of numbers were produced for each object from pixels in each object. Each pixel consists of three (3) numbers representing the colors red, green, and blue. The matrix of numbers were created or computed inRAM 270 when the object(s) were loaded from storage. - The actual analysis for any logo or design in the image of Example I with the “
id 970729” took place inobject analyzer 1001. Because the image with “id 970729” was determined to be an image byobject analyzer 1001, image analyzer method 1002 (seeFIG. 12 ) was executed immediately. Inmethod 1002 the logo or design analysis worked in the following manner: - At the beginning the image with “
id 970729” was loaded into the RAM 270 (seeFIG. 1 ) of thecomputer system 104.RAM 270 created for image with “id 970729” a matrix of numbers comprising: -
91 118 109 121 132 145 114 124 110 115 154 187 212 207 205 220 246 106 126 158 157 129 131 184 210 214 226 242 243 250 247 245 247 248 156 203 232 231 230 231 241 242 239 241 248 253 248 246 245 244 245 175 214 233 228 229 231 243 243 240 240 237 233 231 233 234 226 226 167 197 212 221 217 225 224 221 216 216 215 218 213 205 215 207 216 136 169 198 192 200 199 208 216 206 210 211 200 201 196 214 202 204 121 166 187 197 205 195 209 222 211 208 213 193 198 193 207 191 160 121 173 181 216 210 218 201 199 202 195 196 202 202 187 143 84 60 129 182 197 202 214 218 205 203 188 190 199 185 131 89 51 31 26 157 183 193 194 188 199 186 187 181 183 193 122 42 25 34 34 34 151 180 210 193 181 192 189 175 185 170 180 149 57 37 34 34 34 136 180 202 192 183 203 188 192 174 150 115 122 105 42 34 34 34 131 177 200 193 184 181 182 146 97 64 44 55 139 92 39 34 34 172 183 194 189 179 168 84 56 31 34 33 39 83 136 63 24 33 153 183 183 171 178 169 71 38 28 36 34 34 44 92 96 32 25 140 185 162 162 177 171 128 87 78 80 73 75 74 54 62 53 30 152 181 170 160 124 103 119 115 140 172 149 126 127 65 51 80 65 151 199 170 85 30 14 28 19 103 137 76 40 30 26 46 65 45 156 166 112 23 69 106 64 17 83 61 39 80 76 23 32 58 28 148 158 103 13 90 148 105 35 74 45 64 143 134 53 39 61 39 159 158 129 58 42 51 31 5 97 71 23 66 60 25 45 68 52 192 180 172 139 81 48 69 59 118 150 84 32 41 51 62 76 60 233 223 213 216 211 212 222 204 208 223 206 159 166 171 191 204 183 218 220 217 221 224 232 225 221 228 228 226 227 228 218 216 224 225 96 97 95 92 95 109 106 103 105 104 104 106 96 103 96 102 104 91 249 252 250 25 252 252 253 253 253 244 236 236 242 250 252 106 250 250 246 250 246 244 251 252 249 247 241 234 241 248 246 156 245 241 242 243 223 219 235 239 232 234 233 222 236 236 227 175 216 213 206 147 79 73 167 199 198 197 196 212 195 194 187 167 164 111 68 44 26 34 80 167 209 195 186 187 180 169 172 136 103 44 40 37 34 34 42 114 170 182 167 177 158 153 175 121 131 60 45 23 34 34 36 55 148 178 174 163 155 158 158 121 132 117 44 34 34 34 29 29 74 148 170 159 161 161 163 129 65 150 89 40 34 34 34 27 27 80 167 151 147 139 158 157 40 95 137 62 21 24 34 26 30 43 102 136 143 136 134 151 34 49 108 114 40 27 34 34 34 35 57 112 130 131 127 136 34 30 60 123 88 19 34 34 34 34 28 71 122 122 121 131 34 34 38 79 130 61 35 34 34 18 17 38 88 123 117 172 34 34 34 44 113 127 52 36 35 24 17 34 53 114 87 153 37 36 34 35 63 107 87 38 36 38 32 36 41 73 76 140 83 79 79 81 68 34 96 96 84 85 86 82 78 88 98 152 138 134 112 105 87 25 98 156 126 108 111 117 117 132 100 151 124 81 41 23 31 17 100 106 50 28 27 33 56 81 39 156 86 39 69 93 56 13 85 48 55 85 71 28 51 63 44 148 75 39 123 154 92 26 51 30 89 164 129 25 43 90 51 159 95 31 38 65 33 14 86 62 24 46 57 13 47 72 57 192 137 104 55 30 56 56 107 143 73 31 43 46 63 118 58 233 198 204 180 156 197 180 198 196 195 167 160 173 171 180 153 218 225 214 229 229 220 214 215 205 212 225 203 202 192 175 183 96 92 88 87 86 89 88 82 81 82 87 84 85 81 85 90 - Subsequently, the
computer system 104 executed the content analysis of the image with “id 970729” by source code: -
- Image:=VC_LoadImage24(path);
where “path” was the local location where the image with “id 970729” was stored in object storage device 248 (seeFIGS. 2 and 3A ), which would be “tshirt.jpg” from Example I. “VC_LoadImage” was the function that loaded the image “id 970729” intoRAM 270 where a matrix of numbers was produced. After that, image with “id 970729” was compared with all logos contained in the logos-to-search-templates database 1005 (seeFIG. 12 ), including the “adidas” logo withid 10001, by source code:
- Image:=VC_LoadImage24(path);
- for i :=1 to NumberOfLogos do
-
- begin
- FS_SearchLogo(Image,Logo[i], LogoInfo);
- begin
- end;
- The foregoing function “FS_SearchLogo(Image,Logi[i], LogoInfo)” was a computer vision algorithm that searched for the “adidas” logo with
id 10001 inside the image with “id 970729” by comparing a mathematical template for the “adidas” logo withid 10001 with the matrix of numbers for image with “id 970729.” The computer vision algorithm used for this application was called “Template Matching”. The variable “LogoInfo” held the results of the analysis, storing information about the region where the “adidas” logo withid 10001 was found in image with “id 970729”, and the similarity of that particular region with the searched “adidas” logo. - The “FS_SearchLogo” function created the mathematical model template automatically when the first search for a logo was executed (on demand). The algorithm used for creating the mathematical model was “Create Template”. In this Example II the search was for “adidas” logo with
id 10001. The template matching algorithms required a template for the “adidas” logo which was automatically generated from the known “adidas” logo. The Mathematical Model Template for the known “adidas”logo 10001 comprised: -
Threshold 423434 0 0 0 0.5 1 0 0 0 0 0.5 2 2 0.5 0 0 0.5 2 1.5 1.5 2 0 0.5 2 1.5 1.5 1.5 2 1 2 1.5 1.5 1.5 1.5 1.5 2 2 2 2 2 2 2 2 0 0 0 0 0 0 0 - The following source code caused the discovery of the template for the “adidas”
logo 10001 within the matrix of numbers representing the image with “id 970729”: -
/ / process different image resolutions for (_Step=0; _Step<_Steps; _Step++) { SetCurrentResolution (_Step); / / try to move template step by step over the whole image from top-left to the bottom-right position for (_RegX=_Left; _RegX<_Right; _RegX++) { for (_RegY=_Top; _RegY<_Bottom; _RegY++) { / / calculate match of template double Score = MatchTemplate(10001); / / test if the match is above the calculated threshold from the template if (Score> TemplateThreshold) { / / store results LogoInfo.Score = Score; LogoInfo.Region = (regX, RegY); return; } } } } - The decision whether the template was contained in a particular region of the image with “
id 970729” was made by using a “score” (i.e., the degree of similarity) that expressed how good the template matched a region of the image. If the score was above a desired threshold represented by “Threshold 423434” (e.g. 60%), the process assumed the “adidas” logo withid 10001 was found. Thus, embodiments of the present invention provide determining the region of the object (e.g., image with “id 970729”) where the known object (e.g., “adidas” logo or design with id 10001) is located. - After the “adidas” logo with
id 10001 was successfully found, the results, also called metadata, were stored in object metadata storage device 1003 (seeFIG. 10 ) using the following source code function: - function StoreResultsAndGetNextImage(
-
- const ClientPC: WideString;
- var AnalyseMethod, IDImage: UINT;
- AnalyseResults: OleVariant;
- tFileLoad, tAnalyse, tCOMCall: UINT): WideString;
- In this Example II, the “adidas” logo with “
id 10001” was found in image with “id 970729.” The metadata that was stored in objectmetadata storage device 1003 for this discovery was: -
IMAGE_ID LOGO_ID REGION SCORE 970729 10001 Left: 166 94% Top: 169 Right: 290 Bottom: 240 - The function for storing the metadata in
object metadata device 1003 also retrieved the next image to process from object storage device 248 (seeFIG. 10 ) to begin or repeat the method again. - Thus, by the practice of embodiments of the present inventions, there is broadly provided a system and method for deterring and/or detecting Internet abuse of trademarked intellectual property by identifying imposter or look-alike brands, logos/designs, trademarks or service marks, and by identifying unauthorized Internet sales channels. Embodiments of the present inventions also broadly provide speedy data gathering of possible trademark infringement or dilution cases, including providing URL's of suspect sites for tracking or enforcement purposes and showing areas of potential brand erosion in Internet commerce. Embodiments of the present inventions provide a system to search images (e.g., both text or words and designs or logos in marks) in the Worldwide Internet by specifying the visual image content in means of: text contained in any images; logos or designs contained in any images; faces of people contained in any images including face recognition; and two (2) dimensional objects like animals, cars, etc. contained in any images. Embodiments of the present inventions search a database for images which are substantially identical or similar to any known images. Embodiments of the present inventions also enable people to search the Internet for images that have a specified visual content.
- While the present invention has been described herein with reference to particular embodiments thereof, a latitude of modification, various changes and substitutions are intended in the foregoing disclosure, and it will be appreciated that in some instances some features of the invention will be employed without a corresponding use of other features without departing from the scope and spirit of the invention as set forth. For example, although the network sites are being described as separate and distinct sites, one skilled in the art will recognize that these sites may be part of an integral site, may each include portions of multiple sites, or may include combinations of single and multiple sites. Furthermore, components of this invention may be implemented using a programmed general purpose digital computer, using application specific integrated circuits, or using a network of interconnected conventional components and circuits. As previously indicated, connections may be wired, wireless, modem, etc. Therefore, many modifications may be made to adapt a particular situation or material to the teachings of the invention without departing from the essential scope and spirit of the present invention. It is intended that the invention not be limited to the particular embodiment disclosed as the best mode contemplated for carrying out this invention, but that the invention will include all embodiments and equivalents falling within the scope of the appended claims.
Claims (8)
1. A computer program product for searching a network to identify a target object that is similar to a known object, said computer program product comprising:
a computer readable storage media;
first program instructions to search a network for target objects;
second program instructions to determine if one of said target objects is similar to a known object by comparing, at more than one point of said one target object, a mathematical template associated with pixels of the known object to a matrix of numbers derived from pixels from said one target object; and wherein
said first, second and third program instructions are stored on said computer readable storage media.
2. A computer program product as set forth in claim 1 wherein said mathematical template is associated with pixels that are based on a full-size of the known object.
3. A computer program product as set forth in claim 2 wherein the pixels from said one target object comprise pixels associated with a scaled version of an entirety of said one target object.
4. A computer program product as set forth in claim 1 wherein the pixels associated with the known object comprise pixels associated with a full-size of said known object.
5. A computer program product as set forth in claim 4 wherein the full-size of said known object comprises a complete area of pixels of said known object.
6. A computer program product as set forth in claim 5 wherein each pixel of said known object and said one target object comprises three numbers representing red, green and blue.
7. A computer program product as set forth in claim 1 wherein said one target object comprises a graphical image.
8. A computer program product as set forth in claim 1 wherein said one target object comprises a video image.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/346,988 US20090110298A1 (en) | 2000-12-21 | 2008-12-31 | System and Method for Compiling Images from a Database and Comparing the Compiled Images with Known Images |
US12/837,943 US8107739B2 (en) | 2000-12-21 | 2010-07-16 | System and method for compiling images from a database and comparing the compiled images with known images |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/746,453 US7130466B2 (en) | 2000-12-21 | 2000-12-21 | System and method for compiling images from a database and comparing the compiled images with known images |
US11/585,668 US7499590B2 (en) | 2000-12-21 | 2006-10-24 | System and method for compiling images from a database and comparing the compiled images with known images |
US12/346,988 US20090110298A1 (en) | 2000-12-21 | 2008-12-31 | System and Method for Compiling Images from a Database and Comparing the Compiled Images with Known Images |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/585,668 Continuation US7499590B2 (en) | 2000-12-21 | 2006-10-24 | System and method for compiling images from a database and comparing the compiled images with known images |
Related Child Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/585,668 Continuation US7499590B2 (en) | 2000-12-21 | 2006-10-24 | System and method for compiling images from a database and comparing the compiled images with known images |
US12/837,943 Continuation US8107739B2 (en) | 2000-12-21 | 2010-07-16 | System and method for compiling images from a database and comparing the compiled images with known images |
Publications (1)
Publication Number | Publication Date |
---|---|
US20090110298A1 true US20090110298A1 (en) | 2009-04-30 |
Family
ID=25000908
Family Applications (4)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/746,453 Expired - Lifetime US7130466B2 (en) | 2000-12-21 | 2000-12-21 | System and method for compiling images from a database and comparing the compiled images with known images |
US11/585,668 Expired - Fee Related US7499590B2 (en) | 2000-12-21 | 2006-10-24 | System and method for compiling images from a database and comparing the compiled images with known images |
US12/346,988 Abandoned US20090110298A1 (en) | 2000-12-21 | 2008-12-31 | System and Method for Compiling Images from a Database and Comparing the Compiled Images with Known Images |
US12/837,943 Expired - Fee Related US8107739B2 (en) | 2000-12-21 | 2010-07-16 | System and method for compiling images from a database and comparing the compiled images with known images |
Family Applications Before (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/746,453 Expired - Lifetime US7130466B2 (en) | 2000-12-21 | 2000-12-21 | System and method for compiling images from a database and comparing the compiled images with known images |
US11/585,668 Expired - Fee Related US7499590B2 (en) | 2000-12-21 | 2006-10-24 | System and method for compiling images from a database and comparing the compiled images with known images |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/837,943 Expired - Fee Related US8107739B2 (en) | 2000-12-21 | 2010-07-16 | System and method for compiling images from a database and comparing the compiled images with known images |
Country Status (1)
Country | Link |
---|---|
US (4) | US7130466B2 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120134583A1 (en) * | 2004-05-05 | 2012-05-31 | Google Inc. | Methods and apparatus for automated true object-based image analysis and retrieval |
US11341660B1 (en) * | 2020-03-30 | 2022-05-24 | Amazon Technologies, Inc. | Feature based image detection |
Families Citing this family (118)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6345104B1 (en) * | 1994-03-17 | 2002-02-05 | Digimarc Corporation | Digital watermarks and methods for security documents |
US20010049707A1 (en) | 2000-02-29 | 2001-12-06 | Tran Bao Q. | Systems and methods for generating intellectual property |
US7130466B2 (en) * | 2000-12-21 | 2006-10-31 | Cobion Ag | System and method for compiling images from a database and comparing the compiled images with known images |
JP4300767B2 (en) * | 2002-08-05 | 2009-07-22 | ソニー株式会社 | Guide system, content server, portable device, information processing method, information processing program, and storage medium |
US8117130B2 (en) * | 2003-02-25 | 2012-02-14 | Stragent, Llc | Batch loading and self-registration of digital media files |
US20060294371A1 (en) * | 2003-02-25 | 2006-12-28 | Shawn Fanning | Content Regulation |
US20060167807A1 (en) * | 2003-02-25 | 2006-07-27 | Ali Aydar | Dispute resolution in an open copyright database |
US20060167804A1 (en) * | 2003-02-25 | 2006-07-27 | Ali Aydar | Track listening and playing service for digital media files |
US20060167882A1 (en) * | 2003-02-25 | 2006-07-27 | Ali Aydar | Digital rights management system architecture |
US20060167813A1 (en) * | 2003-02-25 | 2006-07-27 | Ali Aydar | Managing digital media rights through missing masters lists |
US7187787B2 (en) * | 2003-03-14 | 2007-03-06 | Intelitrac, Inc. | Method and apparatus for facial identification enhancement |
EP1460377A3 (en) * | 2003-03-21 | 2004-09-29 | Leica Geosystems AG | Method and device for image processing in a geodetic measuring device |
US7266568B1 (en) * | 2003-04-11 | 2007-09-04 | Ricoh Company, Ltd. | Techniques for storing multimedia information with source documents |
US7664733B2 (en) * | 2003-04-11 | 2010-02-16 | Ricoh Company, Ltd. | Techniques for performing operations on a source symbolic document |
US7206773B2 (en) * | 2003-04-11 | 2007-04-17 | Ricoh Company, Ltd | Techniques for accessing information captured during a presentation using a paper document handout for the presentation |
US20070192867A1 (en) * | 2003-07-25 | 2007-08-16 | Miliefsky Gary S | Security appliances |
US7631060B2 (en) * | 2003-10-23 | 2009-12-08 | Microsoft Corporation | Identity system for use in a computing environment |
US7200608B2 (en) * | 2003-10-23 | 2007-04-03 | Microsoft Corporation | Application programming interface for centralized storage of principal data |
US7831581B1 (en) | 2004-03-01 | 2010-11-09 | Radix Holdings, Llc | Enhanced search |
US20050210008A1 (en) * | 2004-03-18 | 2005-09-22 | Bao Tran | Systems and methods for analyzing documents over a network |
US20050210009A1 (en) * | 2004-03-18 | 2005-09-22 | Bao Tran | Systems and methods for intellectual property management |
CN100419785C (en) * | 2004-04-08 | 2008-09-17 | 佳能株式会社 | Optical symbols indentifying system and method based on use for network service |
US7493596B2 (en) * | 2004-06-30 | 2009-02-17 | International Business Machines Corporation | Method, system and program product for determining java software code plagiarism and infringement |
US7672003B2 (en) * | 2004-09-01 | 2010-03-02 | Eric Morgan Dowling | Network scanner for global document creation, transmission and management |
US20100195538A1 (en) * | 2009-02-04 | 2010-08-05 | Merkey Jeffrey V | Method and apparatus for network packet capture distributed storage system |
JP4759574B2 (en) * | 2004-12-23 | 2011-08-31 | ソレラ ネットワークス インコーポレイテッド | Method and apparatus for network packet capture distributed storage system |
US7783135B2 (en) | 2005-05-09 | 2010-08-24 | Like.Com | System and method for providing objectified image renderings using recognition information from images |
US7660468B2 (en) | 2005-05-09 | 2010-02-09 | Like.Com | System and method for enabling image searching using manual enrichment, classification, and/or segmentation |
WO2006122164A2 (en) * | 2005-05-09 | 2006-11-16 | Riya, Inc. | System and method for enabling the use of captured images through recognition |
US7760917B2 (en) | 2005-05-09 | 2010-07-20 | Like.Com | Computer-implemented method for performing similarity searches |
US7519200B2 (en) * | 2005-05-09 | 2009-04-14 | Like.Com | System and method for enabling the use of captured images through recognition |
US7809192B2 (en) * | 2005-05-09 | 2010-10-05 | Like.Com | System and method for recognizing objects from images and identifying relevancy amongst images and information |
US7657126B2 (en) * | 2005-05-09 | 2010-02-02 | Like.Com | System and method for search portions of objects in images and features thereof |
US8732025B2 (en) * | 2005-05-09 | 2014-05-20 | Google Inc. | System and method for enabling image recognition and searching of remote content on display |
US7657100B2 (en) | 2005-05-09 | 2010-02-02 | Like.Com | System and method for enabling image recognition and searching of images |
US7809722B2 (en) * | 2005-05-09 | 2010-10-05 | Like.Com | System and method for enabling search and retrieval from image files based on recognized information |
US7542610B2 (en) * | 2005-05-09 | 2009-06-02 | Like.Com | System and method for use of images with recognition analysis |
US7945099B2 (en) | 2005-05-09 | 2011-05-17 | Like.Com | System and method for use of images with recognition analysis |
US20080177640A1 (en) | 2005-05-09 | 2008-07-24 | Salih Burak Gokturk | System and method for using image analysis and search in e-commerce |
US20070009139A1 (en) * | 2005-07-11 | 2007-01-11 | Agere Systems Inc. | Facial recognition device for a handheld electronic device and a method of using the same |
US8571272B2 (en) | 2006-03-12 | 2013-10-29 | Google Inc. | Techniques for enabling or establishing the use of face recognition algorithms |
US9690979B2 (en) | 2006-03-12 | 2017-06-27 | Google Inc. | Techniques for enabling or establishing the use of face recognition algorithms |
US20070294396A1 (en) * | 2006-06-15 | 2007-12-20 | Krzaczynski Eryk W | Method and system for researching pestware spread through electronic messages |
US8233702B2 (en) * | 2006-08-18 | 2012-07-31 | Google Inc. | Computer implemented technique for analyzing images |
US7916976B1 (en) | 2006-10-05 | 2011-03-29 | Kedikian Roland H | Facial based image organization and retrieval method |
WO2008046098A2 (en) * | 2006-10-13 | 2008-04-17 | Move, Inc. | Multi-tiered cascading crawling system |
US8527469B2 (en) * | 2006-10-13 | 2013-09-03 | Sony Corporation | System and method for automatic detection of duplicate digital photos |
US8788529B2 (en) * | 2007-02-26 | 2014-07-22 | Microsoft Corp. | Information sharing between images |
US20090199298A1 (en) * | 2007-06-26 | 2009-08-06 | Miliefsky Gary S | Enterprise security management for network equipment |
US8416981B2 (en) * | 2007-07-29 | 2013-04-09 | Google Inc. | System and method for displaying contextual supplemental content based on image content |
RU2007130631A (en) * | 2007-08-10 | 2009-02-20 | Общество с ограниченной ответственностью "Рекогмишн" (RU) | METHOD FOR INDEXING OBJECTS ON DIGITAL IMAGES AND METHOD FOR SEARCHING OBJECTS ON DIGITAL IMAGES |
US20090112861A1 (en) * | 2007-10-30 | 2009-04-30 | Honeywell International, Inc. | Non-word or non-number search |
JP5351409B2 (en) * | 2007-10-31 | 2013-11-27 | キヤノン株式会社 | Position detector, method for obtaining template, exposure apparatus and device manufacturing method |
KR100851435B1 (en) * | 2007-11-28 | 2008-08-11 | (주)올라웍스 | Method and system for providing information based on logo included in digital contents |
US9226047B2 (en) * | 2007-12-07 | 2015-12-29 | Verimatrix, Inc. | Systems and methods for performing semantic analysis of media objects |
US7391886B1 (en) * | 2008-01-09 | 2008-06-24 | International Business Machines Corporation | Digital camera with image tracking system |
EP2250623A4 (en) | 2008-03-05 | 2011-03-23 | Ebay Inc | Method and apparatus for image recognition services |
US9495386B2 (en) * | 2008-03-05 | 2016-11-15 | Ebay Inc. | Identification of items depicted in images |
US8190623B2 (en) * | 2008-06-05 | 2012-05-29 | Enpulz, L.L.C. | Image search engine using image analysis and categorization |
US8004998B2 (en) * | 2008-05-23 | 2011-08-23 | Solera Networks, Inc. | Capture and regeneration of a network data using a virtual software switch |
US8625642B2 (en) | 2008-05-23 | 2014-01-07 | Solera Networks, Inc. | Method and apparatus of network artifact indentification and extraction |
US8521732B2 (en) | 2008-05-23 | 2013-08-27 | Solera Networks, Inc. | Presentation of an extracted artifact based on an indexing technique |
US20090292736A1 (en) * | 2008-05-23 | 2009-11-26 | Matthew Scott Wood | On demand network activity reporting through a dynamic file system and method |
US8555201B2 (en) * | 2008-06-05 | 2013-10-08 | Qualcomm Incorporated | Wireless communication device having deterministic control of foreground access of the user interface |
CN103632288A (en) * | 2008-07-14 | 2014-03-12 | 谷歌股份有限公司 | System and method for using supplemental content items for search criteria for identifying other content items of interest |
US8520979B2 (en) * | 2008-08-19 | 2013-08-27 | Digimarc Corporation | Methods and systems for content processing |
US20110188707A1 (en) * | 2008-09-12 | 2011-08-04 | Halberd Match Corp. | System and Method for Pleographic Subject Identification, Targeting, and Homing Utilizing Electromagnetic Imaging in at Least One Selected Band |
US20100067806A1 (en) * | 2008-09-12 | 2010-03-18 | Halberd Match Corp. | System and method for pleographic recognition, matching, and identification of images and objects |
US20100080411A1 (en) * | 2008-09-29 | 2010-04-01 | Alexandros Deliyannis | Methods and apparatus to automatically crawl the internet using image analysis |
US8401334B2 (en) * | 2008-12-19 | 2013-03-19 | Disney Enterprises, Inc. | Method, system and apparatus for media customization |
US8331677B2 (en) * | 2009-01-08 | 2012-12-11 | Microsoft Corporation | Combined image and text document |
US8825660B2 (en) | 2009-03-17 | 2014-09-02 | Ebay Inc. | Image-based indexing in a network-based marketplace |
KR101404208B1 (en) | 2009-09-29 | 2014-06-11 | 인텔 코오퍼레이션 | Linking disparate content sources |
WO2011060368A1 (en) * | 2009-11-15 | 2011-05-19 | Solera Networks, Inc. | Method and apparatus for storing and indexing high-speed network traffic data |
US20110125748A1 (en) * | 2009-11-15 | 2011-05-26 | Solera Networks, Inc. | Method and Apparatus for Real Time Identification and Recording of Artifacts |
KR20110054776A (en) * | 2009-11-18 | 2011-05-25 | 삼성전자주식회사 | Method and apparatus for obtaining and providing additional information of web resources |
US9164577B2 (en) | 2009-12-22 | 2015-10-20 | Ebay Inc. | Augmented reality system, method, and apparatus for displaying an item image in a contextual environment |
US8572133B2 (en) * | 2010-03-29 | 2013-10-29 | Harris Corporation | System for identifying a selected target in a geographic model and associated methods |
US20110251896A1 (en) * | 2010-04-09 | 2011-10-13 | Affine Systems, Inc. | Systems and methods for matching an advertisement to a video |
US20110254680A1 (en) * | 2010-04-16 | 2011-10-20 | Infrasafe, Inc. | Security monitoring system |
US10127606B2 (en) | 2010-10-13 | 2018-11-13 | Ebay Inc. | Augmented reality system and method for visualizing an item |
US8438163B1 (en) * | 2010-12-07 | 2013-05-07 | Google Inc. | Automatic learning of logos for visual recognition |
US8849991B2 (en) | 2010-12-15 | 2014-09-30 | Blue Coat Systems, Inc. | System and method for hypertext transfer protocol layered reconstruction |
US9116779B2 (en) * | 2010-12-17 | 2015-08-25 | International Business Machines Corporation | Test management domain asset discovery and analysis |
US8666985B2 (en) | 2011-03-16 | 2014-03-04 | Solera Networks, Inc. | Hardware accelerated application-based pattern matching for real time classification and recording of network traffic |
US8799262B2 (en) * | 2011-04-11 | 2014-08-05 | Vistaprint Schweiz Gmbh | Configurable web crawler |
JP6049693B2 (en) * | 2011-04-12 | 2016-12-21 | ナショナル ユニヴァーシティー オブ シンガポール | In-video product annotation using web information mining |
KR20120118383A (en) * | 2011-04-18 | 2012-10-26 | 삼성전자주식회사 | Image compensation device, image processing apparatus and methods thereof |
US8625904B2 (en) * | 2011-08-30 | 2014-01-07 | Intellectual Ventures Fund 83 Llc | Detecting recurring themes in consumer image collections |
US9449342B2 (en) | 2011-10-27 | 2016-09-20 | Ebay Inc. | System and method for visualization of items in an environment using augmented reality |
US9240059B2 (en) | 2011-12-29 | 2016-01-19 | Ebay Inc. | Personal augmented reality |
US9129420B2 (en) | 2012-03-07 | 2015-09-08 | 3D Printlife Llc | Detection of protected subject matter in three dimensional print media |
US8799257B1 (en) * | 2012-03-19 | 2014-08-05 | Google Inc. | Searching based on audio and/or visual features of documents |
US9934522B2 (en) | 2012-03-22 | 2018-04-03 | Ebay Inc. | Systems and methods for batch- listing items stored offline on a mobile device |
US9038178B1 (en) | 2012-06-25 | 2015-05-19 | Emc Corporation | Detection of malware beaconing activities |
US10846766B2 (en) | 2012-06-29 | 2020-11-24 | Ebay Inc. | Contextual menus based on image recognition |
US8903754B2 (en) * | 2012-06-29 | 2014-12-02 | International Business Machines Corporation | Programmatically identifying branding within assets |
CN103679164A (en) * | 2012-09-21 | 2014-03-26 | 阿里巴巴集团控股有限公司 | A method and a system for identifying and processing a mark based on a mobile terminal |
JP2014139734A (en) * | 2013-01-21 | 2014-07-31 | Sony Corp | Information processing device and method, and program |
US9195826B1 (en) * | 2013-05-30 | 2015-11-24 | Emc Corporation | Graph-based method to detect malware command-and-control infrastructure |
US9659033B2 (en) * | 2013-08-19 | 2017-05-23 | Nant Holdings Ip, Llc | Metric based recognition, systems and methods |
US10242400B1 (en) * | 2013-10-25 | 2019-03-26 | Appliance Computing III, Inc. | User interface for image-based rendering of virtual tours |
US9740995B2 (en) * | 2013-10-28 | 2017-08-22 | Morningstar, Inc. | Coordinate-based document processing and data entry system and method |
US9591022B2 (en) | 2014-12-17 | 2017-03-07 | The Boeing Company | Computer defenses and counterattacks |
WO2016123739A1 (en) * | 2015-02-02 | 2016-08-11 | 华为技术有限公司 | Communications system, method for managing communications system, and controller |
US10380166B2 (en) | 2015-06-29 | 2019-08-13 | The Nielson Company (Us), Llc | Methods and apparatus to determine tags for media using multiple media features |
RU2638015C2 (en) | 2015-06-30 | 2017-12-08 | Общество С Ограниченной Ответственностью "Яндекс" | Method for identification of target object on web page |
US10176148B2 (en) * | 2015-08-27 | 2019-01-08 | Microsoft Technology Licensing, Llc | Smart flip operation for grouped objects |
CN107341160B (en) * | 2016-05-03 | 2020-09-01 | 北京京东尚科信息技术有限公司 | Crawler intercepting method and device |
CN107609057B (en) * | 2017-08-25 | 2020-12-22 | 百度在线网络技术(北京)有限公司 | Method and device for acquiring character data of trademark image |
CN110334056A (en) * | 2019-06-24 | 2019-10-15 | 广州探迹科技有限公司 | A kind of crawler result storage method and device based on object storage |
CN111552829B (en) * | 2020-05-07 | 2023-06-27 | 京东科技信息技术有限公司 | Method and apparatus for analyzing image material |
US11080294B1 (en) | 2021-02-03 | 2021-08-03 | Adlumin, Inc. | Systems and methods for data analytics |
US11800056B2 (en) | 2021-02-11 | 2023-10-24 | Logitech Europe S.A. | Smart webcam system |
US11800048B2 (en) | 2021-02-24 | 2023-10-24 | Logitech Europe S.A. | Image generating system with background replacement or modification capabilities |
CN112699089B (en) * | 2021-03-23 | 2021-08-13 | 中国信息通信研究院 | Data sharing system, data sharing method and device |
US11823476B2 (en) | 2021-05-25 | 2023-11-21 | Bank Of America Corporation | Contextual analysis for digital image processing |
US20230065074A1 (en) * | 2021-09-01 | 2023-03-02 | Capital One Services, Llc | Counterfeit object detection using image analysis |
Citations (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5913205A (en) * | 1996-03-29 | 1999-06-15 | Virage, Inc. | Query optimization for visual information retrieval system |
US5983218A (en) * | 1997-06-30 | 1999-11-09 | Xerox Corporation | Multimedia database for use over networks |
US6161109A (en) * | 1998-04-16 | 2000-12-12 | International Business Machines Corporation | Accumulating changes in a database management system by copying the data object to the image copy if the data object identifier of the data object is greater than the image identifier of the image copy |
US6271840B1 (en) * | 1998-09-24 | 2001-08-07 | James Lee Finseth | Graphical search engine visual index |
US6334129B1 (en) * | 1998-01-30 | 2001-12-25 | Canon Kabushiki Kaisha | Data processing apparatus and method |
US6338152B1 (en) * | 1999-10-28 | 2002-01-08 | General Electric Company | Method and system for remotely managing communication of data used for predicting malfunctions in a plurality of machines |
US6445822B1 (en) * | 1999-06-04 | 2002-09-03 | Look Dynamics, Inc. | Search method and apparatus for locating digitally stored content, such as visual images, music and sounds, text, or software, in storage devices on a computer network |
US20020140745A1 (en) * | 2001-01-24 | 2002-10-03 | Ellenby Thomas William | Pointing systems for addressing objects |
US6463426B1 (en) * | 1997-10-27 | 2002-10-08 | Massachusetts Institute Of Technology | Information search and retrieval system |
US6484149B1 (en) * | 1997-10-10 | 2002-11-19 | Microsoft Corporation | Systems and methods for viewing product information, and methods for generating web pages |
US6563959B1 (en) * | 1999-07-30 | 2003-05-13 | Pixlogic Llc | Perceptual similarity image retrieval method |
US6618501B1 (en) * | 1999-05-06 | 2003-09-09 | Canon Kabushiki Kaisha | Object similarity calculation method and apparatus |
US6631364B1 (en) * | 1997-03-26 | 2003-10-07 | National Research Council Of Canada | Method of searching 3-Dimensional images |
US6636635B2 (en) * | 1995-11-01 | 2003-10-21 | Canon Kabushiki Kaisha | Object extraction method, and image sensing apparatus using the method |
US6718063B1 (en) * | 1998-12-11 | 2004-04-06 | Canon Kabushiki Kaisha | Method and apparatus for computing the similarity between images |
US6751363B1 (en) * | 1999-08-10 | 2004-06-15 | Lucent Technologies Inc. | Methods of imaging based on wavelet retrieval of scenes |
US6804683B1 (en) * | 1999-11-25 | 2004-10-12 | Olympus Corporation | Similar image retrieving apparatus, three-dimensional image database apparatus and method for constructing three-dimensional image database |
US6834288B2 (en) * | 2001-04-13 | 2004-12-21 | Industrial Technology Research Institute | Content-based similarity retrieval system for image data |
US7130466B2 (en) * | 2000-12-21 | 2006-10-31 | Cobion Ag | System and method for compiling images from a database and comparing the compiled images with known images |
US20070130112A1 (en) * | 2005-06-30 | 2007-06-07 | Intelligentek Corp. | Multimedia conceptual search system and associated search method |
US20070233622A1 (en) * | 2006-03-31 | 2007-10-04 | Alex Willcock | Method and system for computerized searching and matching using emotional preference |
US20080046312A1 (en) * | 2006-08-15 | 2008-02-21 | Ehud Shany | Method and system for target marketing over the internet and interactive tv |
Family Cites Families (162)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4223380A (en) | 1978-04-06 | 1980-09-16 | Ncr Corporation | Distributed multiprocessor communication system |
JPS55112651A (en) | 1979-02-21 | 1980-08-30 | Fujitsu Ltd | Virtual computer system |
US4672609A (en) | 1982-01-19 | 1987-06-09 | Tandem Computers Incorporated | Memory system with operation error detection |
US4773028A (en) | 1984-10-01 | 1988-09-20 | Tektronix, Inc. | Method and apparatus for improved monitoring and detection of improper device operation |
US4819234A (en) | 1987-05-01 | 1989-04-04 | Prime Computer, Inc. | Operating system debugger |
CA1314101C (en) | 1988-02-17 | 1993-03-02 | Henry Shao-Lin Teng | Expert system for security inspection of a digital computer system in a network environment |
US5121345A (en) | 1988-11-03 | 1992-06-09 | Lentz Stephen A | System and method for protecting integrity of computer data and software |
US4975950A (en) | 1988-11-03 | 1990-12-04 | Lentz Stephen A | System and method of protecting integrity of computer data and software |
US5347450A (en) | 1989-01-18 | 1994-09-13 | Intel Corporation | Message routing in a multiprocessor computer system |
US5353393A (en) * | 1989-06-14 | 1994-10-04 | Sunwest Trading Corporation | Apparatus and method for manipulating scanned documents in a computer aided design system |
US5204966A (en) | 1990-03-09 | 1993-04-20 | Digital Equipment Corporation | System for controlling access to a secure system by verifying acceptability of proposed password by using hashing and group of unacceptable passwords |
EP0449242A3 (en) | 1990-03-28 | 1992-10-28 | National Semiconductor Corporation | Method and structure for providing computer security and virus prevention |
US5032979A (en) | 1990-06-22 | 1991-07-16 | International Business Machines Corporation | Distributed security auditing subsystem for an operating system |
US5210704A (en) | 1990-10-02 | 1993-05-11 | Technology International Incorporated | System for prognosis and diagnostics of failure and wearout monitoring and for prediction of life expectancy of helicopter gearboxes and other rotating equipment |
US5274824A (en) | 1991-03-01 | 1993-12-28 | Bull Hn Information Systems Inc. | Keyring metaphor for user's security keys on a distributed multiprocess data system |
JPH04310188A (en) * | 1991-03-01 | 1992-11-02 | Internatl Business Mach Corp <Ibm> | Library service method for document/image library |
EP0510244A1 (en) | 1991-04-22 | 1992-10-28 | Acer Incorporated | Method and apparatus for protecting a computer system from computer viruses |
US5774727A (en) | 1991-06-27 | 1998-06-30 | Digital Equipment Corporation | Parallel processing system for virtual processor implementation of machine-language instructions |
US5577209A (en) | 1991-07-11 | 1996-11-19 | Itt Corporation | Apparatus and method for providing multi-level security for communication among computers and terminals on a network |
US5309562A (en) | 1991-08-19 | 1994-05-03 | Multi-Tech Systems, Inc. | Method and apparatus for establishing protocol spoofing from a modem |
US5454074A (en) | 1991-09-18 | 1995-09-26 | The Boeing Company | Electronic checklist system |
US5649095A (en) | 1992-03-30 | 1997-07-15 | Cozza; Paul D. | Method and apparatus for detecting computer viruses through the use of a scan information cache |
US5278901A (en) | 1992-04-30 | 1994-01-11 | International Business Machines Corporation | Pattern-oriented intrusion-detection system and method |
US5311593A (en) | 1992-05-13 | 1994-05-10 | Chipcom Corporation | Security system for a network concentrator |
US5359659A (en) | 1992-06-19 | 1994-10-25 | Doren Rosenthal | Method for securing software against corruption by computer viruses |
US5371852A (en) | 1992-10-14 | 1994-12-06 | International Business Machines Corporation | Method and apparatus for making a cluster of computers appear as a single host on a network |
US5345595A (en) | 1992-11-12 | 1994-09-06 | Coral Systems, Inc. | Apparatus and method for detecting fraudulent telecommunication activity |
JP2501771B2 (en) | 1993-01-19 | 1996-05-29 | インターナショナル・ビジネス・マシーンズ・コーポレイション | Method and apparatus for obtaining multiple valid signatures of an unwanted software entity |
US5440723A (en) | 1993-01-19 | 1995-08-08 | International Business Machines Corporation | Automatic immune system for computers and computer networks |
US5586260A (en) | 1993-02-12 | 1996-12-17 | Digital Equipment Corporation | Method and apparatus for authenticating a client to a server in computer systems which support different security mechanisms |
GB9303527D0 (en) | 1993-02-22 | 1993-04-07 | Hewlett Packard Ltd | Network analysis method |
AU671194B2 (en) | 1993-02-23 | 1996-08-15 | British Telecommunications Public Limited Company | Event correlation |
US5630061A (en) | 1993-04-19 | 1997-05-13 | International Business Machines Corporation | System for enabling first computer to communicate over switched network with second computer located within LAN by using media access control driver in different modes |
US5398196A (en) | 1993-07-29 | 1995-03-14 | Chambers; David A. | Method and apparatus for detection of computer viruses |
US5414833A (en) | 1993-10-27 | 1995-05-09 | International Business Machines Corporation | Network security system and method using a parallel finite state machine adaptive active monitor and responder |
US5606668A (en) | 1993-12-15 | 1997-02-25 | Checkpoint Software Technologies Ltd. | System for securing inbound and outbound data packet flow in a computer network |
US5835726A (en) | 1993-12-15 | 1998-11-10 | Check Point Software Technologies Ltd. | System for securing the flow of and selectively modifying packets in a computer network |
US5515508A (en) | 1993-12-17 | 1996-05-07 | Taligent, Inc. | Client server system and method of operation including a dynamically configurable protocol stack |
US5974457A (en) | 1993-12-23 | 1999-10-26 | International Business Machines Corporation | Intelligent realtime monitoring of data traffic |
US5557742A (en) | 1994-03-07 | 1996-09-17 | Haystack Labs, Inc. | Method and system for detecting intrusion into and misuse of a data processing system |
US5522026A (en) | 1994-03-18 | 1996-05-28 | The Boeing Company | System for creating a single electronic checklist in response to multiple faults |
US5675711A (en) | 1994-05-13 | 1997-10-07 | International Business Machines Corporation | Adaptive statistical regression and classification of data strings, with application to the generic detection of computer viruses |
JPH10501354A (en) | 1994-06-01 | 1998-02-03 | クワンタム・リープ・イノヴェーションズ・インコーポレーテッド | Computer virus trap device |
US5999711A (en) | 1994-07-18 | 1999-12-07 | Microsoft Corporation | Method and system for providing certificates holding authentication and authorization information for users/machines |
US5623601A (en) | 1994-11-18 | 1997-04-22 | Milkway Networks Corporation | Apparatus and method for providing a secure gateway for communication and data exchanges between networks |
US5764890A (en) | 1994-12-13 | 1998-06-09 | Microsoft Corporation | Method and system for adding a secure network server to an existing computer network |
CA2138302C (en) | 1994-12-15 | 1999-05-25 | Michael S. Fortinsky | Provision of secure access to external resources from a distributed computing environment |
US5590331A (en) | 1994-12-23 | 1996-12-31 | Sun Microsystems, Inc. | Method and apparatus for generating platform-standard object files containing machine-independent code |
JPH08242229A (en) | 1995-03-01 | 1996-09-17 | Fujitsu Ltd | State matching processing system for monitoring network |
US5696486A (en) | 1995-03-29 | 1997-12-09 | Cabletron Systems, Inc. | Method and apparatus for policy-based alarm notification in a distributed network management environment |
US5749066A (en) | 1995-04-24 | 1998-05-05 | Ericsson Messaging Systems Inc. | Method and apparatus for developing a neural network for phoneme recognition |
US5734697A (en) | 1995-04-28 | 1998-03-31 | Mci Corporation | Method and apparatus for improving telecommunications system performance |
US5790799A (en) | 1995-05-17 | 1998-08-04 | Digital Equipment Corporation | System for sampling network packets by only storing the network packet that its error check code matches with the reference error check code |
US5878420A (en) | 1995-08-31 | 1999-03-02 | Compuware Corporation | Network monitoring and management system |
US5623600A (en) | 1995-09-26 | 1997-04-22 | Trend Micro, Incorporated | Virus detection and removal apparatus for computer networks |
US5765030A (en) | 1996-07-19 | 1998-06-09 | Symantec Corp | Processor emulator module having a variable pre-fetch queue size for program execution |
US6067410A (en) * | 1996-02-09 | 2000-05-23 | Symantec Corporation | Emulation repair system |
US5696822A (en) | 1995-09-28 | 1997-12-09 | Symantec Corporation | Polymorphic virus detection module |
US5826013A (en) | 1995-09-28 | 1998-10-20 | Symantec Corporation | Polymorphic virus detection module |
US5854916A (en) | 1995-09-28 | 1998-12-29 | Symantec Corporation | State-based cache for antivirus software |
US5745692A (en) | 1995-10-23 | 1998-04-28 | Ncr Corporation | Automated systems administration of remote computer servers |
US5838903A (en) | 1995-11-13 | 1998-11-17 | International Business Machines Corporation | Configurable password integrity servers for use in a shared resource environment |
US5832211A (en) | 1995-11-13 | 1998-11-03 | International Business Machines Corporation | Propagating plain-text passwords from a main registry to a plurality of foreign registries |
US5764887A (en) | 1995-12-11 | 1998-06-09 | International Business Machines Corporation | System and method for supporting distributed computing mechanisms in a local area network server environment |
GB9526129D0 (en) | 1995-12-21 | 1996-02-21 | Philips Electronics Nv | Machine code format translation |
JP3165366B2 (en) | 1996-02-08 | 2001-05-14 | 株式会社日立製作所 | Network security system |
JPH09214493A (en) | 1996-02-08 | 1997-08-15 | Hitachi Ltd | Network system |
JPH09223389A (en) * | 1996-02-15 | 1997-08-26 | Mitsubishi Electric Corp | Synchronous semiconductor storage device |
US5761504A (en) | 1996-02-16 | 1998-06-02 | Motorola, Inc. | Method for updating a software code in a communication system |
US5950012A (en) | 1996-03-08 | 1999-09-07 | Texas Instruments Incorporated | Single chip microprocessor circuits, systems, and methods for self-loading patch micro-operation codes and patch microinstruction codes |
US5964839A (en) | 1996-03-29 | 1999-10-12 | At&T Corp | System and method for monitoring information flow and performing data collection |
US6377994B1 (en) * | 1996-04-15 | 2002-04-23 | International Business Machines Corporation | Method and apparatus for controlling server access to a resource in a client/server system |
US5822517A (en) | 1996-04-15 | 1998-10-13 | Dotan; Eyal | Method for detecting infection of software programs by memory resident software viruses |
US6014645A (en) * | 1996-04-19 | 2000-01-11 | Block Financial Corporation | Real-time financial card application system |
US5881236A (en) | 1996-04-26 | 1999-03-09 | Hewlett-Packard Company | System for installation of software on a remote computer system over a network using checksums and password protection |
US5884033A (en) | 1996-05-15 | 1999-03-16 | Spyglass, Inc. | Internet filtering system for filtering data transferred over the internet utilizing immediate and deferred filtering actions |
US5798706A (en) | 1996-06-18 | 1998-08-25 | Raptor Systems, Inc. | Detecting unauthorized network communication |
US5857191A (en) | 1996-07-08 | 1999-01-05 | Gradient Technologies, Inc. | Web application server with secure common gateway interface |
US5787177A (en) | 1996-08-01 | 1998-07-28 | Harris Corporation | Integrated network security access control system |
US5828833A (en) | 1996-08-15 | 1998-10-27 | Electronic Data Systems Corporation | Method and system for allowing remote procedure calls through a network firewall |
US5864665A (en) | 1996-08-20 | 1999-01-26 | International Business Machines Corporation | Auditing login activity in a distributed computing environment |
US5832208A (en) | 1996-09-05 | 1998-11-03 | Cheyenne Software International Sales Corp. | Anti-virus agent for use with databases and mail servers |
US5845067A (en) | 1996-09-09 | 1998-12-01 | Porter; Jack Edward | Method and apparatus for document management utilizing a messaging system |
US5892903A (en) | 1996-09-12 | 1999-04-06 | Internet Security Systems, Inc. | Method and apparatus for detecting and identifying security vulnerabilities in an open network computer communication system |
US5983350A (en) | 1996-09-18 | 1999-11-09 | Secure Computing Corporation | Secure firewall supporting different levels of authentication based on address or encryption status |
US5899999A (en) * | 1996-10-16 | 1999-05-04 | Microsoft Corporation | Iterative convolution filter particularly suited for use in an image classification and retrieval system |
US5991881A (en) | 1996-11-08 | 1999-11-23 | Harris Corporation | Network surveillance system |
US5796942A (en) | 1996-11-21 | 1998-08-18 | Computer Associates International, Inc. | Method and apparatus for automated network-wide surveillance and security breach intervention |
US5848233A (en) | 1996-12-09 | 1998-12-08 | Sun Microsystems, Inc. | Method and apparatus for dynamic packet filter assignment |
US5974237A (en) | 1996-12-18 | 1999-10-26 | Northern Telecom Limited | Communications network monitoring |
US5987611A (en) | 1996-12-31 | 1999-11-16 | Zone Labs, Inc. | System and methodology for managing internet access on a per application basis for client computers connected to the internet |
US5875296A (en) | 1997-01-28 | 1999-02-23 | International Business Machines Corporation | Distributed file system web server user authentication with cookies |
US5983270A (en) | 1997-03-11 | 1999-11-09 | Sequel Technology Corporation | Method and apparatus for managing internetwork and intranetwork activity |
US5925126A (en) | 1997-03-18 | 1999-07-20 | Memco Software, Ltd. | Method for security shield implementation in computer system's software |
US5987606A (en) | 1997-03-19 | 1999-11-16 | Bascom Global Internet Services, Inc. | Method and system for content filtering information retrieved from an internet computer network |
US5964889A (en) | 1997-04-16 | 1999-10-12 | Symantec Corporation | Method to analyze a program for presence of computer viruses by examining the opcode for faults before emulating instruction in emulator |
JP3028783B2 (en) * | 1997-04-25 | 2000-04-04 | 日本電気株式会社 | Network monitoring method and device |
US5922051A (en) | 1997-05-14 | 1999-07-13 | Ncr Corporation | System and method for traffic management in a network management system |
JP3464121B2 (en) * | 1997-06-11 | 2003-11-05 | 沖電気工業株式会社 | Viterbi decoding method and Viterbi decoding device |
US6073172A (en) * | 1997-07-14 | 2000-06-06 | Freegate Corporation | Initializing and reconfiguring a secure network interface |
EP0898245B1 (en) * | 1997-08-05 | 2004-04-14 | Canon Kabushiki Kaisha | Image processing method and apparatus |
US5919257A (en) | 1997-08-08 | 1999-07-06 | Novell, Inc. | Networked workstation intrusion detection system |
US5978917A (en) | 1997-08-14 | 1999-11-02 | Symantec Corporation | Detection and elimination of macro viruses |
US6016553A (en) * | 1997-09-05 | 2000-01-18 | Wild File, Inc. | Method, software and apparatus for saving, using and recovering data |
US5983348A (en) | 1997-09-10 | 1999-11-09 | Trend Micro Incorporated | Computer network malicious code scanner |
US5961644A (en) | 1997-09-19 | 1999-10-05 | International Business Machines Corporation | Method and apparatus for testing the integrity of computer security alarm systems |
US6357008B1 (en) * | 1997-09-23 | 2002-03-12 | Symantec Corporation | Dynamic heuristic method for detecting computer viruses using decryption exploration and evaluation phases |
US5991856A (en) | 1997-09-30 | 1999-11-23 | Network Associates, Inc. | System and method for computer operating system protection |
US6003132A (en) | 1997-10-22 | 1999-12-14 | Rvt Technologies, Inc. | Method and apparatus for isolating a computer system upon detection of viruses and similar data |
US6041347A (en) * | 1997-10-24 | 2000-03-21 | Unified Access Communications | Computer system and computer-implemented process for simultaneous configuration and monitoring of a computer network |
US6035323A (en) * | 1997-10-24 | 2000-03-07 | Pictra, Inc. | Methods and apparatuses for distributing a collection of digital media over a network with automatic generation of presentable media |
US6026442A (en) * | 1997-11-24 | 2000-02-15 | Cabletron Systems, Inc. | Method and apparatus for surveillance in communications networks |
US6052709A (en) * | 1997-12-23 | 2000-04-18 | Bright Light Technologies, Inc. | Apparatus and method for controlling delivery of unsolicited electronic mail |
US6029256A (en) * | 1997-12-31 | 2000-02-22 | Network Associates, Inc. | Method and system for allowing computer programs easy access to features of a virus scanning engine |
US6035423A (en) * | 1997-12-31 | 2000-03-07 | Network Associates, Inc. | Method and system for providing automated updating and upgrading of antivirus applications using a computer network |
US5987610A (en) | 1998-02-12 | 1999-11-16 | Ameritech Corporation | Computer virus screening methods and systems |
US6195687B1 (en) * | 1998-03-18 | 2001-02-27 | Netschools Corporation | Method and apparatus for master-slave control in a educational classroom communication network |
US6628824B1 (en) * | 1998-03-20 | 2003-09-30 | Ken Belanger | Method and apparatus for image identification and comparison |
US6725378B1 (en) * | 1998-04-15 | 2004-04-20 | Purdue Research Foundation | Network protection for denial of service attacks |
US6408391B1 (en) * | 1998-05-06 | 2002-06-18 | Prc Inc. | Dynamic system defense for information warfare |
US6070190A (en) * | 1998-05-11 | 2000-05-30 | International Business Machines Corporation | Client-based application availability and response monitoring and reporting for distributed computing environments |
US6173413B1 (en) * | 1998-05-12 | 2001-01-09 | Sun Microsystems, Inc. | Mechanism for maintaining constant permissions for multiple instances of a device within a cluster |
US6397242B1 (en) * | 1998-05-15 | 2002-05-28 | Vmware, Inc. | Virtualization system including a virtual machine monitor for a computer with a segmented architecture |
US6347374B1 (en) * | 1998-06-05 | 2002-02-12 | Intrusion.Com, Inc. | Event detection |
US6185689B1 (en) * | 1998-06-24 | 2001-02-06 | Richard S. Carson & Assoc., Inc. | Method for network self security assessment |
US6134664A (en) | 1998-07-06 | 2000-10-17 | Prc Inc. | Method and system for reducing the volume of audit data and normalizing the audit data received from heterogeneous sources |
US6547139B1 (en) * | 1998-07-10 | 2003-04-15 | Welch Allyn Data Collection, Inc. | Method and apparatus for extending operating range of bar code scanner |
US6661904B1 (en) * | 1998-07-15 | 2003-12-09 | Personalogo | Method and system for automated electronic conveyance of hidden data |
US6711127B1 (en) * | 1998-07-31 | 2004-03-23 | General Dynamics Government Systems Corporation | System for intrusion detection and vulnerability analysis in a telecommunications signaling network |
US6327388B1 (en) * | 1998-08-14 | 2001-12-04 | Matsushita Electric Industrial Co., Ltd. | Identification of logos from document images |
US6338141B1 (en) * | 1998-09-30 | 2002-01-08 | Cybersoft, Inc. | Method and apparatus for computer virus detection, analysis, and removal in real time |
US6230288B1 (en) * | 1998-10-29 | 2001-05-08 | Network Associates, Inc. | Method of treating whitespace during virus detection |
US6321338B1 (en) * | 1998-11-09 | 2001-11-20 | Sri International | Network surveillance |
US6530024B1 (en) * | 1998-11-20 | 2003-03-04 | Centrax Corporation | Adaptive feedback security system and method |
US6517587B2 (en) * | 1998-12-08 | 2003-02-11 | Yodlee.Com, Inc. | Networked architecture for enabling automated gathering of information from Web servers |
US6226372B1 (en) * | 1998-12-11 | 2001-05-01 | Securelogix Corporation | Tightly integrated cooperative telecommunications firewall and scanner with distributed capabilities |
US6574737B1 (en) * | 1998-12-23 | 2003-06-03 | Symantec Corporation | System for penetrating computer or computer network |
US6205552B1 (en) * | 1998-12-31 | 2001-03-20 | Mci Worldcom, Inc. | Method and apparatus for checking security vulnerability of networked devices |
US6578147B1 (en) * | 1999-01-15 | 2003-06-10 | Cisco Technology, Inc. | Parallel intrusion detection sensors with load balancing for high speed networks |
US6647139B1 (en) * | 1999-02-18 | 2003-11-11 | Matsushita Electric Industrial Co., Ltd. | Method of object recognition, apparatus of the same and recording medium therefor |
US6510523B1 (en) * | 1999-02-22 | 2003-01-21 | Sun Microsystems Inc. | Method and system for providing limited access privileges with an untrusted terminal |
US6839850B1 (en) * | 1999-03-04 | 2005-01-04 | Prc, Inc. | Method and system for detecting intrusion into and misuse of a data processing system |
US6405318B1 (en) * | 1999-03-12 | 2002-06-11 | Psionic Software, Inc. | Intrusion detection system |
US6681331B1 (en) * | 1999-05-11 | 2004-01-20 | Cylant, Inc. | Dynamic software system intrusion detection |
US6405365B1 (en) * | 1999-07-02 | 2002-06-11 | Cisco Technology, Inc. | Computer program command generator and parser |
US6519647B1 (en) * | 1999-07-23 | 2003-02-11 | Microsoft Corporation | Methods and apparatus for synchronizing access control in a web server |
US6691232B1 (en) * | 1999-08-05 | 2004-02-10 | Sun Microsystems, Inc. | Security architecture with environment sensitive credential sufficiency evaluation |
JP2001092972A (en) * | 1999-09-24 | 2001-04-06 | Mamoru Minami | Image recognizing method |
US6584454B1 (en) * | 1999-12-31 | 2003-06-24 | Ge Medical Technology Services, Inc. | Method and apparatus for community management in remote system servicing |
US6535227B1 (en) * | 2000-02-08 | 2003-03-18 | Harris Corporation | System and method for assessing the security posture of a network and having a graphical user interface |
US6792144B1 (en) * | 2000-03-03 | 2004-09-14 | Koninklijke Philips Electronics N.V. | System and method for locating an object in an image using models |
US6956569B1 (en) * | 2000-03-30 | 2005-10-18 | Nec Corporation | Method for matching a two dimensional image to one of a plurality of three dimensional candidate models contained in a database |
US20020112237A1 (en) * | 2000-04-10 | 2002-08-15 | Kelts Brett R. | System and method for providing an interactive display interface for information objects |
US6519703B1 (en) * | 2000-04-14 | 2003-02-11 | James B. Joyce | Methods and apparatus for heuristic firewall |
IL152502A0 (en) | 2000-04-28 | 2003-05-29 | Internet Security Systems Inc | Method and system for managing computer security information |
US6718383B1 (en) * | 2000-06-02 | 2004-04-06 | Sun Microsystems, Inc. | High availability networking with virtual IP address failover |
US6353385B1 (en) * | 2000-08-25 | 2002-03-05 | Hyperon Incorporated | Method and system for interfacing an intrusion detection system to a central alarm system |
US7124440B2 (en) * | 2000-09-07 | 2006-10-17 | Mazu Networks, Inc. | Monitoring network traffic denial of service attacks |
US20020032793A1 (en) * | 2000-09-08 | 2002-03-14 | The Regents Of The University Of Michigan | Method and system for reconstructing a path taken by undesirable network traffic through a computer network from a source of the traffic |
US20020083331A1 (en) * | 2000-12-21 | 2002-06-27 | 802 Systems, Inc. | Methods and systems using PLD-based network communication protocols |
US7844696B2 (en) * | 2001-06-27 | 2010-11-30 | Arbor Networks, Inc. | Method and system for monitoring control signal traffic over a computer network |
US6546493B1 (en) * | 2001-11-30 | 2003-04-08 | Networks Associates Technology, Inc. | System, method and computer program product for risk assessment scanning based on detected anomalous events |
-
2000
- 2000-12-21 US US09/746,453 patent/US7130466B2/en not_active Expired - Lifetime
-
2006
- 2006-10-24 US US11/585,668 patent/US7499590B2/en not_active Expired - Fee Related
-
2008
- 2008-12-31 US US12/346,988 patent/US20090110298A1/en not_active Abandoned
-
2010
- 2010-07-16 US US12/837,943 patent/US8107739B2/en not_active Expired - Fee Related
Patent Citations (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6636635B2 (en) * | 1995-11-01 | 2003-10-21 | Canon Kabushiki Kaisha | Object extraction method, and image sensing apparatus using the method |
US5913205A (en) * | 1996-03-29 | 1999-06-15 | Virage, Inc. | Query optimization for visual information retrieval system |
US6631364B1 (en) * | 1997-03-26 | 2003-10-07 | National Research Council Of Canada | Method of searching 3-Dimensional images |
US5983218A (en) * | 1997-06-30 | 1999-11-09 | Xerox Corporation | Multimedia database for use over networks |
US6484149B1 (en) * | 1997-10-10 | 2002-11-19 | Microsoft Corporation | Systems and methods for viewing product information, and methods for generating web pages |
US6463426B1 (en) * | 1997-10-27 | 2002-10-08 | Massachusetts Institute Of Technology | Information search and retrieval system |
US6334129B1 (en) * | 1998-01-30 | 2001-12-25 | Canon Kabushiki Kaisha | Data processing apparatus and method |
US6161109A (en) * | 1998-04-16 | 2000-12-12 | International Business Machines Corporation | Accumulating changes in a database management system by copying the data object to the image copy if the data object identifier of the data object is greater than the image identifier of the image copy |
US6271840B1 (en) * | 1998-09-24 | 2001-08-07 | James Lee Finseth | Graphical search engine visual index |
US6718063B1 (en) * | 1998-12-11 | 2004-04-06 | Canon Kabushiki Kaisha | Method and apparatus for computing the similarity between images |
US6618501B1 (en) * | 1999-05-06 | 2003-09-09 | Canon Kabushiki Kaisha | Object similarity calculation method and apparatus |
US6445822B1 (en) * | 1999-06-04 | 2002-09-03 | Look Dynamics, Inc. | Search method and apparatus for locating digitally stored content, such as visual images, music and sounds, text, or software, in storage devices on a computer network |
US6563959B1 (en) * | 1999-07-30 | 2003-05-13 | Pixlogic Llc | Perceptual similarity image retrieval method |
US6751363B1 (en) * | 1999-08-10 | 2004-06-15 | Lucent Technologies Inc. | Methods of imaging based on wavelet retrieval of scenes |
US6338152B1 (en) * | 1999-10-28 | 2002-01-08 | General Electric Company | Method and system for remotely managing communication of data used for predicting malfunctions in a plurality of machines |
US6804683B1 (en) * | 1999-11-25 | 2004-10-12 | Olympus Corporation | Similar image retrieving apparatus, three-dimensional image database apparatus and method for constructing three-dimensional image database |
US7130466B2 (en) * | 2000-12-21 | 2006-10-31 | Cobion Ag | System and method for compiling images from a database and comparing the compiled images with known images |
US20020140745A1 (en) * | 2001-01-24 | 2002-10-03 | Ellenby Thomas William | Pointing systems for addressing objects |
US6834288B2 (en) * | 2001-04-13 | 2004-12-21 | Industrial Technology Research Institute | Content-based similarity retrieval system for image data |
US20070130112A1 (en) * | 2005-06-30 | 2007-06-07 | Intelligentek Corp. | Multimedia conceptual search system and associated search method |
US20070233622A1 (en) * | 2006-03-31 | 2007-10-04 | Alex Willcock | Method and system for computerized searching and matching using emotional preference |
US20080046312A1 (en) * | 2006-08-15 | 2008-02-21 | Ehud Shany | Method and system for target marketing over the internet and interactive tv |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120134583A1 (en) * | 2004-05-05 | 2012-05-31 | Google Inc. | Methods and apparatus for automated true object-based image analysis and retrieval |
US8903199B2 (en) | 2004-05-05 | 2014-12-02 | Google Inc. | Methods and apparatus for automated true object-based image analysis and retrieval |
US8908997B2 (en) | 2004-05-05 | 2014-12-09 | Google Inc. | Methods and apparatus for automated true object-based image analysis and retrieval |
US8908996B2 (en) * | 2004-05-05 | 2014-12-09 | Google Inc. | Methods and apparatus for automated true object-based image analysis and retrieval |
US9424277B2 (en) | 2004-05-05 | 2016-08-23 | Google Inc. | Methods and apparatus for automated true object-based image analysis and retrieval |
US11341660B1 (en) * | 2020-03-30 | 2022-05-24 | Amazon Technologies, Inc. | Feature based image detection |
Also Published As
Publication number | Publication date |
---|---|
US20110013843A1 (en) | 2011-01-20 |
US20020114522A1 (en) | 2002-08-22 |
US20070127823A1 (en) | 2007-06-07 |
US8107739B2 (en) | 2012-01-31 |
US7499590B2 (en) | 2009-03-03 |
US7130466B2 (en) | 2006-10-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7130466B2 (en) | System and method for compiling images from a database and comparing the compiled images with known images | |
US7801893B2 (en) | Similarity detection and clustering of images | |
US7769772B2 (en) | Mixed media reality brokerage network with layout-independent recognition | |
KR100980748B1 (en) | System and methods for creation and use of a mixed media environment | |
US7587412B2 (en) | Mixed media reality brokerage network and methods of use | |
US6628824B1 (en) | Method and apparatus for image identification and comparison | |
US8019118B2 (en) | Digital media recognition apparatus and methods | |
CN101297319B (en) | Embedding hot spots in electronic documents | |
US9087104B2 (en) | Dynamic presentation of targeted information in a mixed media reality recognition system | |
US8190621B2 (en) | Method, system, and computer readable recording medium for filtering obscene contents | |
US7672543B2 (en) | Triggering applications based on a captured text in a mixed media environment | |
US6772145B2 (en) | Search method in a used car search support system | |
US20070047782A1 (en) | System And Methods For Creation And Use Of A Mixed Media Environment With Geographic Location Information | |
US20070050341A1 (en) | Triggering applications for distributed action execution and use of mixed media recognition as a control input | |
US20070136680A1 (en) | System and method for selecting pictures for presentation with text content | |
JP2005038421A (en) | Information management system and method | |
KR20060061307A (en) | Method and system for augmenting web content | |
US7421416B2 (en) | Method of managing web sites registered in search engine and a system thereof | |
EP2482210A2 (en) | System and methods for creation and use of a mixed media environment | |
US20080071553A1 (en) | Generation of Commercial Presentations | |
KR100876214B1 (en) | Apparatus and method for context aware advertising and computer readable medium processing the method | |
JP2002297648A (en) | Device and program for information retrieval, and recording medium | |
Sees | Use of Another's Trademark in a Web Page Meta Tag: Why Liability Should Not Ensue Under the Lanham Act for Trademark Infringement | |
JP2003132061A (en) | Monitoring device of home page and monitoring method thereof | |
Sivakumar et al. | Review Made on the Content-Based Image Recovery |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |
|
AS | Assignment |
Owner name: KYNDRYL, INC., NEW YORK Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INTERNATIONAL BUSINESS MACHINES CORPORATION;REEL/FRAME:058213/0912 Effective date: 20211118 |