US20100125451A1 - Natural Language Recognition Using Context Information - Google Patents
Natural Language Recognition Using Context Information Download PDFInfo
- Publication number
- US20100125451A1 US20100125451A1 US12/691,725 US69172510A US2010125451A1 US 20100125451 A1 US20100125451 A1 US 20100125451A1 US 69172510 A US69172510 A US 69172510A US 2010125451 A1 US2010125451 A1 US 2010125451A1
- Authority
- US
- United States
- Prior art keywords
- paper
- data
- based document
- recognition
- sensing device
- 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/171—Editing, e.g. inserting or deleting by use of digital ink
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/22—Character recognition characterised by the type of writing
- G06V30/226—Character recognition characterised by the type of writing of cursive writing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/24—Character recognition characterised by the processing or recognition method
- G06V30/242—Division of the character sequences into groups prior to recognition; Selection of dictionaries
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
Definitions
- the present invention relates to a method of and system for natural language recognition, and in particular, to a method of and system for computer-based recognition of natural language data implemented on a distributed computer network.
- IVR interactive voice response
- automated cheque-processing systems automated form data-entry systems.
- FIG. 1 An example of a three-tiered distributed system architecture is depicted in FIG. 1 (prior art), illustrating a system 100 which includes a client layer 110 , network layer 120 and application layer 130 .
- Client device 140 communicates with one or more servers 150 which in turn communicate with one or more applications 160 .
- the combination of distributed computing and pattern recognition techniques has made possible the development of systems such as NetpageTM by Silverbrook Research Pty Ltd, an interactive paper-based interface to online information. Systems such as this give users the ability to interact with information from any location that provides network connectivity (including wireless network access) using familiar human-communication techniques such as handwriting or speech.
- FIG. 2 The basic processing steps of presently known pattern recognition systems are depicted in FIG. 2 (prior art). Processing begins when an input device 210 generates a signal 220 that is to be recognized by the system 100 (that is, to be classified as belonging to a specific class or sequence of class elements). Usually, one or more pre-processing procedures 230 are applied to remove noise and produce a normalized signal 240 , which is then segmented 250 to produce a stream of primitive elements 260 required for a classification procedure 270 . Note that often this segmentation 250 is “soft”, meaning that a number of potential segmentation points are located, and the final segmentation points are resolved during classification 270 or context processing 290 .
- the segmented signal 260 is then passed to a classifier 270 where a representative set of features is extracted from the signal and used in combination with a pre-defined model 275 of the input signal to produce a set of symbol hypotheses 280 .
- These hypotheses 280 give an indication of the probability that a sequence of segments within the signal represent a basic symbolic element (e.g. letter, word, phoneme, etc.).
- the context-processing module 290 uses the symbol hypotheses 280 generated by the classifier 270 to decode the signal according to a specified context model 295 (such as a dictionary or character grammar).
- the result 297 produced by the context processing 290 is passed to the application 299 for interpretation and further processing.
- Natural language input is inconsistent, noisy, and ambiguous, leading to potential recognition and decoding errors.
- high recognition accuracy is required for pattern recognition applications to operate successfully, since mistakes can be expensive and frustrating to users.
- recognition systems should make use of as much contextual information as possible to increase the possibility of correctly recognizing the natural language input. For example, when recognizing a signal that must represent a country name, the recognition system can use a pre-defined list of valid country names to guide the recognition procedure. Similarly, when recognizing a phone number, a limited symbol set (i.e. digits) can be used to constrain the recognition results.
- the problem domain for many pattern recognition systems is inherently ambiguous (i.e. many of the input patterns encountered during processing cannot be accurately classified without further information from a different source).
- Digital ink is a digital representation of the information generated by a pen-based input device.
- digital ink is structured as a sequence of strokes that begin when the pen device makes contact with a drawing surface and ends when the pen-based input device is lifted. Each stroke comprises a set of sampled coordinates that define the movement of the pen-based input device whilst the pen-based input device is in contact with the drawing surface.
- Handwriting typically involves writing in a mixture of writing styles (e.g. cursive, discrete, run-on etc.), a variety of fonts and scripts and different layouts (e.g. mixing drawings with text, various text line orientations etc.).
- writing styles e.g. cursive, discrete, run-on etc.
- fonts and scripts e.g. mixing drawings with text, various text line orientations etc.
- handwriting recognition accuracy remains relatively low, and the number of errors introduced by recognition (both for the database entries and for the handwritten query) means that present techniques do not work well.
- the process of converting handwriting into text results in the loss of a significant amount of information regarding the general shape and dynamic properties of the ink.
- the identification of individual characters is highly ambiguous.
- Paragraph, Inc. offers a network-based distributed handwriting recognition system called “NetCalif” (ParaGraph, Handwriting Recognition for Internet Connected Device, November 1999) that is based on their Calligraphy handwriting recognition software.
- Philips has developed “SpeechMagic”, a client/server-based, professional speech recognition software package (Philips, SpeechMagic 4.0, 2000). This system supports specialized vocabularies (called ConTexts) and dictation, recognition, and correction can be done, independently of the location, across a LAN, WAN, or the Internet.
- ConTexts specialized vocabularies
- dictation, recognition, and correction can be done, independently of the location, across a LAN, WAN, or the Internet.
- a user has access to one or more terminals which are capable of requesting and/or receiving information or data from local or remote information sources.
- the information source in the present context, may be a database associated with an application.
- a terminal may be a type of processing system, computer or computerised device, personal computer (PC), mobile, cellular or satellite telephone, mobile data terminal, portable computer, Personal Digital Assistant (PDA), pager, thin client, or any other similar type of digital electronic device.
- PC personal computer
- PDA Personal Digital Assistant
- pager pager
- thin client or any other similar type of digital electronic device.
- the capability of such a terminal to request and/or receive information or data can be provided by software, hardware and/or firmware.
- a terminal may include or be associated with other devices, for example a pen-based input device for handwriting input or a microphone for speech input.
- An information source can include a server, or any type of terminal, that may be associated with one or more storage devices that are able to store information or data, such as digital ink, for example in one or more databases residing on a storage device.
- the exchange of information i.e., the request and/or receipt of information or data
- the communication means can be realised by physical cables, for example a metallic cable such as a telephone line, semi-conducting cables, electromagnetic signals, for example radio-frequency signals or infra-red signals, optical fibre cables, satellite links or any other such medium or combination thereof connected to a network infrastructure.
- a method of recognising digital ink input by a user into a computer-based digital ink recognition system the user interacting with a paper-based document, the paper-based document having disposed therein or thereon coded data indicative of a particular field of the paper-based document and of at least one reference point of the paper-based document, the method including the steps of:
- decoding by the sensing device at least some of the coded data to form indicating data indicative of the identity of the field of the paper-based document containing the coded data and at least one of a position and a movement of the sensing device relative to the paper-based document;
- FIG. 1 (prior art) illustrates a distributed system architecture
- FIG. 2 illustrates a flow chart of basic pattern recognition steps
- FIG. 3 illustrates an example processing system able to be used as a server to house a recognizer, according to a particular embodiment of the present invention
- FIG. 4 illustrates an example distributed recognition system, according to a particular embodiment of the present invention
- FIG. 5 illustrates an example of ambiguous handwriting input for “clog”/“dog”
- FIG. 6 illustrates an example of ambiguous handwriting input for “tile”/“lite”
- FIG. 7 illustrates an example recognition scenario, according to a particular embodiment of the present invention.
- FIG. 8 illustrates an example recognizer selection scenario, according to a particular embodiment of the present invention
- FIG. 9 illustrates an example recognizer training scenario, according to a particular embodiment of the present invention.
- FIG. 10 illustrates an example recognizer registration scenario, according to a particular embodiment of the present invention.
- the processing system 300 generally includes at least one processor 302 , or processing unit or plurality of processors, memory 304 and at least one output device 308 , coupled together via a bus or group of buses 310 .
- At least one storage device 314 which houses at least one database 316 can also be provided, which may be remote and accessed via a network.
- the memory 304 can be any form of memory device, for example, volatile or non-volatile memory, solid state storage devices, magnetic devices, etc.
- the processor 302 could include more than one distinct processing device, for example to handle different functions within the processing system 300 .
- Input device 306 for example a pen-based input device or a microphone, is normally remote to the system 300 .
- Input device 306 is used by a user to generate natural language data 318 which is preferably transmitted over network 307 to system 300 for processing.
- Output device 308 produces or generates intermediate format data 320 , for example for transmission over a network, to be transmitted to application 324 , which could be remote or local to the system 300 .
- the storage device 314 can be any form of data or information storage means, for example, volatile or non-volatile memory, solid state storage devices, magnetic devices, etc.
- the processing system 300 may be a server and is adapted to allow data or information to be stored in and/or retrieved from, via wired or wireless communication means, the at least one database 316 , which may be remote and accessed via a further network.
- the processor 302 receives natural language data 318 from input device 306 , preferably via network 307 , and outputs intermediate format data 320 by utilising output device 308 , for example a network interface.
- the application 324 may return decoded data to the processing system.
- the application 324 may cause information to be printed, for example on a NetpageTM printer, at a user's location. More than one input device 306 can be provided.
- processing system 300 may be any form of terminal, server, specialised hardware, or the like.
- the processing system 300 may be a part of a networked communications system.
- the application 324 may initiate transfer of natural language data 318 from the input device 306 to server 300 .
- the server 300 is part of a system for computer-based recognition of natural language data, the system implemented on a network and comprising: the input device 306 to obtain natural language data; server 300 to receive the natural language data 318 via a network 307 ; a recognizer residing on the server 300 to process, in processor 302 , the natural language data 318 to produce intermediate format data 320 ; and, an application 324 to receive the intermediate format data 320 and to decode the intermediate format data 320 into computer-readable format data using context information associated with the application 324 .
- the present invention is configured to work with the NetpageTM networked computer system, a detailed description of which is given in the applicant's co-pending applications, including in particular, PCT Publication No. WO0242989 entitled “Sensing Device” filed 30 May 2002, PCT Publication No. WO0242894 entitled “Interactive Printer” filed 30 May 2002, PCT Publication No. WO0214075 “Interface Surface Printer Using Invisible Ink” filed 21 Feb. 2002, PCT Publication No. WO0242950 “Apparatus For Interaction With A Network Computer System” filed 30 May 2002, and PCT Publication No. WO03034276 entitled “Digital Ink Database Searching Using Handwriting Feature Synthesis” filed 24 Apr. 2003.
- the preferred form of the Netpage system provides an interactive paper-based interface to online information by utilizing pages of invisibly coded paper and an optically imaging pen.
- Each page generated by the Netpage system is uniquely identified and stored on a network server, and all user interaction with the paper using the Netpage pen is captured, interpreted, and stored.
- Digital printing technology facilitates the on-demand printing of Netpage documents, allowing interactive applications to be developed.
- the Netpage printer, pen, and network infrastructure provide a paper-based alternative to traditional screen-based applications and online publishing services, and supports user-interface functionality such as hypertext navigation and form input.
- a printer receives a document from a publisher or application provider via a broadband connection, which is printed with an invisible pattern of infrared tags that each encodes the location of the tag on the page and a unique page identifier.
- the imaging pen decodes these tags and converts the motion of the pen into digital ink.
- the digital ink is transmitted over a wireless channel to a relay base station, and then sent to the network for processing and storage.
- the system uses a stored description of the page to interpret the digital ink, and performs the requested actions by interacting with an application.
- Applications provide content to the user by publishing documents, and process the digital ink interactions submitted by the user.
- an application generates one or more interactive pages in response to user input, which are transmitted to the network to be stored, rendered, and finally printed as output to the user.
- the Netpage system allows sophisticated applications to be developed by providing services for document publishing, rendering, and delivery, authenticated transactions and secure payments, handwriting recognition and digital ink searching, and user validation using biometric techniques such as signature verification.
- FIG. 4 An example architecture for a distributed pattern recognition system 400 is depicted in FIG. 4 .
- a signal 410 is recorded by an input device 415 at a client layer 420 and transmitted over a network to a server (network layer 430 ) for recognition by a recognizer 440 , with the intermediate results 445 transmitted back to the client layer 420 or a third party application 450 on an application layer 455 for interpretation and processing.
- client devices 415 and distributed applications 450 do not require the significant computing resources commonly needed to perform natural language pattern recognition, and the network servers that perform the recognition are not subject to the resource constraints that are inherent in many client devices 415 (e.g. mobile phones, personal-digital assistants, imaging pens, etc.).
- network servers are able to use extremely processor- and/or memory-intensive techniques to improve recognition accuracy, and can use hardware optimised to perform the specific recognition task.
- Performing pattern recognition on a centralized server also offers an advantage to pattern-recognition systems that employ user-specific adaptation to achieve higher recognition rates.
- some handwriting recognition techniques develop a handwriting model for each user of the system based on previous recognition results, which is then used to improve the future accuracy of the system for that user (see for example L. Schomaker, H. Teulings, E. Helsper, and G. Abbink, “Adaptive Recognition Of Online, Cursive Handwriting”, Proceedings of the Sixth International Conference on Handwriting and Drawing. Paris, July, 4-7 Telecom, (pp. 19-21), 1993 and S. Connell and A. K. Jain, “Writer Adaptation of Online Handwritten Models,” Proc. 5th International Conference on Document Analysis and Recognition, Bangalore, India, pp. 434-437, September 1999).
- This adaptation is more effective if a single server, or set of servers, performs all recognition for a user (rather than a large number of individual applications each performing their own recognition), since the server is able to perform adaptation based on the input generated by all applications.
- centralized server-based pattern recognition simplifies the management of the recognition system 400 by allowing recognizers to be reconfigured and upgraded without interaction with the distributed client devices 415 and applications 450 , and allows training and test data to be easily collected.
- FIG. 4 A solution to this problem is to use a mechanism for distributed recognition as depicted in FIG. 4 .
- a user When a user generates a signal (i.e. natural language data) 410 to be recognized and processed by an application, the signal 410 is submitted to a distributed server for processing.
- the server performs processing steps such as pre-processing, segmentation, and classification (see FIG. 2 ), but does not use a context model to decode the result (or only performs partial decoding as described in the following discussion). Rather, the intermediate recognition results (i.e. intermediate format data) are returned or sent to the application allowing the application to apply any arbitrarily complex and domain-specific context processing to decode the signal.
- One method of returning the intermediate recognition results (i.e. intermediate format data) to an application is to use a symbol DAG (Directed Acyclic Graph), which is a generic data structure that contains symbol and associated scores as vertices, and valid transitions between symbols as edges.
- the structure can be implemented as a two-dimensional array of elements, each of which defines the output generated by the pattern classifier for a single segment of the signal and the associated valid transitions for that segment.
- This structure represents all the potential recognition alternatives that may be derived from the input signal based on the results of the classifier.
- the application uses this structure, in combination with a context model, to decode the input signal.
- the symbol DAG is equivalent to a matrix where each column contains the results of the classification of a single segment of the input signal. Each element in the column represents the probability that the classified segment is a particular symbol, and includes an offset that indicates the next possible segment (column) in the input signal that can follow this symbol.
- the matrix represents all the possible decoding paths based on the output of the pattern classifier. These paths and associated classification scores can be combined with a context model to fully decode the input signal.
- the symbol DAG is applicable in any pattern recognition task where a sequence of classification results is decoded using a context or set of constraints.
- the symbols contained in the symbol DAG may be any primitive element that is generated as the output of a pattern classifier, including the output from a time-series classifier. Examples of such recognition systems include handwriting and speech recognition, protein sequencing (see A. C. Camproux, P. Tuffery, S. Hazout, “Hidden Markov Model Approach For Identifying The Modular Framework Of The Protein Backbone”, Protein engineering, 12(12), pp. 1063, December 1999), image processing and computer vision (see Y. He, A.
- Table 1 shows a symbol DAG that represents the output from a handwritten character recognizer generated by the ambiguous text given in FIG. 5 .
- the recognizer has found two possible character segmentation arrangements, as depicted by the two rows in the symbol DAG.
- the symbol scores are given as probabilities; however, an actual implementation may typically use log-probabilities (i.e. the base-10 logarithm of the probability result) to improve the performance of context processing and to avoid overflow and underflow problems that occur when multiplying probabilities using finite precision floating-point operations.
- the context processor starts with the first entry in the DAG (i.e. the character ‘c’).
- the score for this entry is added to the accumulated total (since log-probabilities are added rather than multiplied), and processing moves to the column given by the offset value in the entry (in this example, column 1).
- two alternatives exist (i.e. “cl” or “cb”), and the scores for these alternatives are found by adding the scores to the previous total.
- the decoding continues until the end of the DAG is reached.
- the second entry in column 0 i.e. the character ‘d’
- column 1 is skipped in this traversal of the DAG, as indicated by the offset value of 2 in the character score entry. This is due to the letter ‘d’ being constructed using two strokes, and thus the recognition of the letters ‘l’ and ‘b’ cannot be valid in this alternative.
- the potential decoding alternatives in this example are:
- the DAG structure must ensure that strokes are assigned to an individual letter only once. To do this, alternate paths must be defined to ensure that if a stroke is assigned to a letter, no subsequent letter may use that stroke in its construction.
- An example of this is given in FIG. 6 , with the derived DAG depicted in Table 2.
- the short, horizontal marks can potentially be recognized as crossbar elements of a letter ‘t’, or diacritical marks for the letter ‘i’. However, if a marking is used as a crossbar, it cannot subsequently be used as a diacritical.
- the potential decoding alternatives in this example are:
- the character value of a DAG entry can be set to zero, indicating a NUL character (i.e. a character that does not change the text, but will modify the text probability).
- a NUL character i.e. a character that does not change the text, but will modify the text probability.
- word break positions i.e. spaces
- SPACE/NUL pair indicating that there is a certain probability that a space appears at that point in the DAG.
- a distributed recognition system 700 may support a number of different recognizers 440 that are controlled by a distributed recognition management system or recognition manager 710 .
- These recognizers 440 can include systems capable of supporting different classes of recognition, such as different languages, dialects, or accents, or cursive or boxed input for handwriting systems.
- the application 450 first queries 720 the recognition manager 710 to find a recognizer 440 that matches the parameters of the input to be recognized (as depicted in FIG. 8 ).
- the recognition manager 710 queries 730 each recognizer 440 to find a recognizer that supports the parameters specified by the application 450 .
- a recognizer 440 When a recognizer 440 indicates support 740 (as opposed to no support 750 from recognizer 440 a in FIG. 8 ) for the specified parameter set, the enumeration ends and the selected recognizer 440 (in the case of FIG. 8 recognizer 440 b ) is passed 760 to the application 450 .
- the individual recognizers 440 do not need to be centralized and may be distributed throughout the system 700 , since the recognition manager 710 acts as a controller for the set of recognizers 440 .
- the application 450 can then request processing by the selected recognizer by passing or directing 770 the signal and parameters to the selected recognizer 440 .
- Intermediate format data 445 i.e. a symbol lattice, is returned to the application 450 and the application 450 can return a response 780 to the input device 415 .
- Distributed recognition systems can also support user dictionaries, which are user-specific word lists (and possibly associated a-priori probabilities) that include words that a user writes frequently but which are unlikely to appear in a standard dictionary (examples include company names, work or personal interest specific terms, etc.).
- User dictionaries can be stored and managed centrally so that words added to the dictionary when using one application are available to all applications for context processing. Obviously, applications can manage and use their own local user-specific dictionaries if required, since they have full control over context decoding.
- the centralized recognition system When an application requires the recognition of a signal that may contain words found in the user dictionary (e.g. standard handwritten text input such as the subject line of an e-mail or an arbitrary voice message), the centralized recognition system generates the usual intermediate recognition results to be returned to the application for context decoding. However, in addition to this it decodes the intermediate results using the user-dictionary as a language model, the result of which is also returned to the application.
- These two intermediate results structures can be combined by the application during its context decoding to generate a final decoding that includes the user-specific dictionary information.
- Distributed recognition systems may also support user-specific training for a recognizer 440 , as depicted in FIG. 9 .
- the data generated by a user-specific recognition training application is submitted 910 to the centralized recognition manager 710 , which stores 920 the data in a database 930 .
- the recognition manager 710 then enumerates all recognizers 440 to determine if they support the data format as defined by the parameters associated with the training data, and if so (True signal 940 ), submits the training data 950 to the recognizer 440 for user-specific training
- the recognition manager 710 queries 1010 the training database 930 to determine if any training data 1020 of the format required by the recognizer 440 exists. If so, the training data 1020 is submitted to the newly registered recognizer 440 for processing, as depicted in FIG. 10 .
- the invention may also be said to broadly consist in the parts, elements and features referred to or indicated herein, individually or collectively, in any or all combinations of two or more of the parts, elements or features, and wherein specific integers are mentioned herein which have known equivalents in the art to which the invention relates, such known equivalents are deemed to be incorporated herein as if individually set forth.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Character Discrimination (AREA)
Abstract
A method of recognising digital ink input by a user into a computer-based digital ink recognition system is disclosed. The user interacts with a paper-based document. The paper-based document has disposed thereon coded data indicative of a particular field of the paper-based document and of at least one reference point of the paper-based document. An image sensor in a sensing device captures images of at least some of the coded data when the sensing device is placed in an operative position relative to the paper-based document. The sensing device then decodes at least some of the coded data to form indicating data indicative of the identity of the field of the paper-based document containing the coded data and at least one of a position and a movement of the sensing device relative to the paper-based document. A server receives the indicating data from the sensing device, and processes the indicating data using a recognizer residing on the server to produce intermediate format data. The intermediate format data is then transmitted to an application which decodes the intermediate format data into computer-readable format data using context information associated with the paper-based document.
Description
- The present application is a continuation application of U.S. patent application Ser. No. 10/510,392 filed on Oct. 7, 2004, which is a 371 of PCT/AU04/001088 filed on Aug. 16, 2004, the content of is herein incorporated by reference.
- The present invention relates to a method of and system for natural language recognition, and in particular, to a method of and system for computer-based recognition of natural language data implemented on a distributed computer network.
- Various methods, systems and apparatus relating to the present invention are disclosed in the following granted US patents and co-pending US applications filed by the applicant or assignee of the present application: The disclosures of all of these granted US patents and co-pending US applications are incorporated herein by reference.
-
10/815,621 7,243,835 10/815,630 10/815,637 10/815,638 7,251,050 10/815,642 7,097,094 7,137,549 10/815,618 7,156,292 10/815,635 7,357,323 10/815,634 7,137,566 7,131,596 7,128,265 7,197,374 7,175,089 10/815,617 7,537,160 7,506,808 7,207,483 7,296,737 7,270,266 10/815,614 7,605,940 7,128,270 7,457,007 7,150,398 7,159,777 7,450,273 7,188,769 7,097,106 7,070,110 7,243,849 7,204,941 7,282,164 7,465,342 7,156,289 7,178,718 7,225,979 09/575,197 7,079,712 6,825,945 7,330,974 6,813,039 7,190,474 6,987,506 6,824,044 6,980,318 6,816,274 7,102,772 7,350,236 6,681,045 6,678,499 6,679,420 6,963,845 6,976,220 6,728,000 7,110,126 7,173,722 6,976,035 6,813,558 6,766,942 6,965,454 6,995,859 7,088,459 6,720,985 7,286,113 6,922,779 6,978,019 6,847,883 7,131,058 7,295,839 7,406,445 7,533,031 6,959,298 6,973,450 7,150,404 6,965,882 7,233,924 09/575,181 7,593,899 7,175,079 7,162,259 6,718,061 7,464,880 7,012,710 6,825,956 7,451,115 7,222,098 7,590,561 7,263,508 7,031,010 6,972,864 6,862,105 7,009,738 6,989,911 6,982,807 7,518,756 6,829,387 6,714,678 6,644,545 6,609,653 6,651,879 10/291,555 7,293,240 7,467,185 7,415,668 7,044,363 7,004,390 6,867,880 7,034,953 6,987,581 7,216,224 7,506,153 7,162,269 7,162,222 7,290,210 7,293,233 7,293,234 6,850,931 6,865,570 6,847,961 10/685,583 7,162,442 10/685,584 7,159,784 7,557,944 7,404,144 6,889,896 10/831,232 7,174,056 7,068,382 7,007,851 6,957,921 6,457,883 7,094,910 7,091,344 7,122,685 7,038,066 7,099,019 7,062,651 6,789,194 6,789,191 7,529,936 7,278,018 6,644,642 6,502,614 6,622,999 6,669,385 6,827,116 6,549,935 6,987,573 6,727,996 6,591,884 6,439,706 6,760,119 7,295,332 7,064,851 6,826,547 6,290,349 6,428,155 6,785,016 6,831,682 6,741,871 6,927,871 6,980,306 6,965,439 6,840,606 7,036,918 6,977,746 6,970,264 7,068,389 7,093,991 7,190,491 6,982,798 6,870,966 6,822,639 6,474,888 6,627,870 6,724,374 6,788,982 7,263,270 6,788,293 6,946,672 6,737,591 7,091,960 7,369,265 6,792,165 7,105,753 6,795,593 6,980,704 6,768,821 7,132,612 7,041,916 6,797,895 7,015,901 7,289,882 7,148,644 10/778,056 10/778,058 10/778,060 7,515,186 7,567,279 10/778,062 10/778,061 10/778,057 7,096,199 7,055,739 7,233,320 6,830,196 6,832,717 7,182,247 7,082,562 6,843,420 10/291,718 6,789,731 7,057,608 6,766,944 6,766,945 7,289,103 7,412,651 7,299,969 7,108,192 7,111,791 7,077,333 6,983,878 7,564,605 7,134,598 7,431,219 6,929,186 6,994,264 7,017,826 7,014,123 7,630,554 7,526,128 6,957,768 7,456,820 7,170,499 7,106,888 7,123,239 6,982,701 6,982,703 7,227,527 6,786,397 6,947,027 6,975,299 7,139,431 7,048,178 7,118,025 6,839,053 7,015,900 7,010,147 7,133,557 6,914,593 7,437,671 6,454,482 6,808,330 6,527,365 6,474,773 6,550,997 7,093,923 6,957,923 7,131,724 - Recent advances in pattern classification have enabled the development of sophisticated software systems that can recognize natural language data (i.e. natural language user input) such as speech (see for example L. Rabiner and B. Juang, “Fundamentals of Speech Recognition”, Prentice Hall, Englewood Cliffs, N.J., 1993) or handwriting (see for example G. Lorette, “Handwriting Recognition or Reading? Situation At The Dawn of the 3rd Millennium”, Advances In Handwriting Recognition, Series in Machine Perception and Artificial Intelligence, Vol. 34, pp. 3-15, World Scientific Publishing Co. 1999).
- These applications allow users to communicate with a computerised system in a natural and convenient way, and permit the automation of tasks that previously required human input. Some examples of such applications include interactive voice response (IVR) systems, automated cheque-processing systems and automated form data-entry systems.
- In addition, the growth of networked computing and the Internet has enabled the development of complex distributed systems, and the existence of open, standardized protocols has allowed the integration of end-user devices, centralized servers, and applications. An example of a three-tiered distributed system architecture is depicted in
FIG. 1 (prior art), illustrating asystem 100 which includes aclient layer 110,network layer 120 andapplication layer 130. Client device 140 communicates with one ormore servers 150 which in turn communicate with one ormore applications 160. The combination of distributed computing and pattern recognition techniques has made possible the development of systems such as Netpage™ by Silverbrook Research Pty Ltd, an interactive paper-based interface to online information. Systems such as this give users the ability to interact with information from any location that provides network connectivity (including wireless network access) using familiar human-communication techniques such as handwriting or speech. - The basic processing steps of presently known pattern recognition systems are depicted in
FIG. 2 (prior art). Processing begins when aninput device 210 generates asignal 220 that is to be recognized by the system 100 (that is, to be classified as belonging to a specific class or sequence of class elements). Usually, one or more pre-processingprocedures 230 are applied to remove noise and produce a normalizedsignal 240, which is then segmented 250 to produce a stream ofprimitive elements 260 required for a classification procedure 270. Note that often thissegmentation 250 is “soft”, meaning that a number of potential segmentation points are located, and the final segmentation points are resolved during classification 270 orcontext processing 290. - The segmented
signal 260 is then passed to a classifier 270 where a representative set of features is extracted from the signal and used in combination with a pre-definedmodel 275 of the input signal to produce a set ofsymbol hypotheses 280. Thesehypotheses 280 give an indication of the probability that a sequence of segments within the signal represent a basic symbolic element (e.g. letter, word, phoneme, etc.). After classification 270, the context-processing module 290 uses thesymbol hypotheses 280 generated by the classifier 270 to decode the signal according to a specified context model 295 (such as a dictionary or character grammar). The result 297 produced by thecontext processing 290 is passed to theapplication 299 for interpretation and further processing. - Natural language input is inconsistent, noisy, and ambiguous, leading to potential recognition and decoding errors. However, high recognition accuracy is required for pattern recognition applications to operate successfully, since mistakes can be expensive and frustrating to users. As a result, recognition systems should make use of as much contextual information as possible to increase the possibility of correctly recognizing the natural language input. For example, when recognizing a signal that must represent a country name, the recognition system can use a pre-defined list of valid country names to guide the recognition procedure. Similarly, when recognizing a phone number, a limited symbol set (i.e. digits) can be used to constrain the recognition results. The problem domain for many pattern recognition systems is inherently ambiguous (i.e. many of the input patterns encountered during processing cannot be accurately classified without further information from a different source).
- The following discussion refers to handwriting by way of background information, however, the present invention should not be considered to be limited to application to only handwriting as the form of natural language data input.
- Digital ink is a digital representation of the information generated by a pen-based input device. Generally, digital ink is structured as a sequence of strokes that begin when the pen device makes contact with a drawing surface and ends when the pen-based input device is lifted. Each stroke comprises a set of sampled coordinates that define the movement of the pen-based input device whilst the pen-based input device is in contact with the drawing surface.
- As an example, one of the major issues faced in the development of highly accurate handwriting recognition systems is the inherent ambiguity of handwriting (e.g. the letters ‘u’ and ‘v’, ‘t’ and ‘f’, and ‘g’ and ‘y’ are often written with a very similar appearance and are thus easily confused). Human readers rely on contextual knowledge to correctly decode handwritten text, and as a result a large amount of research has been directed at applying syntactic and linguistic constraints to handwritten text recognition (see for example: H. Beigi and T. Fujisaki, “A Character Level Predictive Language Model and Its Application to Handwriting Recognition”, Proceedings of the Canadian Conference on Electrical and Computer Engineering, Toronto, Canada, Sep. 13-16, 1992; U. Marti and H. Bunke, “Handwritten Sentence Recognition”, Proceedings of the 15th International Conference on Pattern Recognition, Barcelona, Spain, Volume 3, pp. 467-470, 2000; D. Bouchaffra, V. Govindaraju, and S. Srihari, “Postprocessing of Recognized Strings Using Nonstationary Markovian Models”, IEEE Transactions Pattern Analysis and Machine Intelligence, 21(10), pp. 990-999, October 1999; J. Pitrelli and E. Ratzlaff, “Quantifying the Contribution of Language Modeling to Writer-Independent On-line Handwriting Recognition”, Proceedings of the Seventh International Workshop on Frontiers in Handwriting Recognition, Amsterdam, September 11-13, 2000; R. Srihari, “Use of Lexical and Syntactic Techniques in Recognizing Handwritten Text”, ARPA Workshop on Human Language Technology, Princeton, N.J., March 1994; and L. Yaeger, B. Webb, and R. Lyon, “Combining Neural Networks and Context-Driven Search for On-Line, Printed Handwriting Recognition in the Newton”, AI Magazine, Volume 19, No. 1, pp. 73-89, AAAI 1998).
- The increasing use of pen-based computing and the emergence of paper-based interfaces to networked computing resources (see for example: Anoto, “Anoto, Ericsson, and Time Manager Take Pen and Paper into the Digital Age with the Anoto Technology”, Press Release, 6 Apr. 2000; and Y. Chans, Z. Lei, D. Lopresti, and S. Kung, “A Feature Based Approach For Image Retrieval by Sketch”, Proceedings of SPIE Volume 3229: Multimedia Storage and Archiving Systems II, 1997) has highlighted the need for techniques to interpret digital ink. Pen-based computing allows users to interact with applications.
- As a result of the progress in pen-based interface research, handwritten digital ink documents, represented by time-ordered sequences of sampled pen strokes, are becoming increasingly popular (J. Subrahmonia and T. Zimmerman: Pen Computing: Challenges and Applications. Proceedings of the ICPR, 2000, pp. 2060-2066). Handwriting typically involves writing in a mixture of writing styles (e.g. cursive, discrete, run-on etc.), a variety of fonts and scripts and different layouts (e.g. mixing drawings with text, various text line orientations etc.).
- Presently, handwriting recognition accuracy remains relatively low, and the number of errors introduced by recognition (both for the database entries and for the handwritten query) means that present techniques do not work well. The process of converting handwriting into text results in the loss of a significant amount of information regarding the general shape and dynamic properties of the ink. In many handwriting styles (particularly cursive writing), the identification of individual characters is highly ambiguous.
- Similar work has been performed in the field of speech recognition, natural language processing, and machine translation.
- Some known natural language recognition systems currently exist. Paragraph, Inc. offers a network-based distributed handwriting recognition system called “NetCalif” (ParaGraph, Handwriting Recognition for Internet Connected Device, November 1999) that is based on their Calligraphy handwriting recognition software. The user's natural handwriting—cursive, print, or a combination of both—is captured by client software, then transmitted from an Internet-connected device to the NetCalif servers where it is converted and returned as typewritten text to the client device.
- Philips has developed “SpeechMagic”, a client/server-based, professional speech recognition software package (Philips, SpeechMagic 4.0, 2000). This system supports specialized vocabularies (called ConTexts) and dictation, recognition, and correction can be done, independently of the location, across a LAN, WAN, or the Internet.
- In a networked information or data communications system, a user has access to one or more terminals which are capable of requesting and/or receiving information or data from local or remote information sources. The information source, in the present context, may be a database associated with an application. In such a communications system, a terminal may be a type of processing system, computer or computerised device, personal computer (PC), mobile, cellular or satellite telephone, mobile data terminal, portable computer, Personal Digital Assistant (PDA), pager, thin client, or any other similar type of digital electronic device. The capability of such a terminal to request and/or receive information or data can be provided by software, hardware and/or firmware. A terminal may include or be associated with other devices, for example a pen-based input device for handwriting input or a microphone for speech input.
- An information source can include a server, or any type of terminal, that may be associated with one or more storage devices that are able to store information or data, such as digital ink, for example in one or more databases residing on a storage device. The exchange of information (i.e., the request and/or receipt of information or data) between a terminal and an information source, or other terminal(s), is facilitated by a communication means. The communication means can be realised by physical cables, for example a metallic cable such as a telephone line, semi-conducting cables, electromagnetic signals, for example radio-frequency signals or infra-red signals, optical fibre cables, satellite links or any other such medium or combination thereof connected to a network infrastructure.
- The reference to any prior art in this specification is not, and should not be taken as, an acknowledgment or any form of suggestion that such prior art forms part of the common general knowledge.
- According to an aspect of the present invention there is provided a method of recognising digital ink input by a user into a computer-based digital ink recognition system, the user interacting with a paper-based document, the paper-based document having disposed therein or thereon coded data indicative of a particular field of the paper-based document and of at least one reference point of the paper-based document, the method including the steps of:
- capturing by an image sensor in a sensing device images of at least some of the coded data when the sensing device is placed in an operative position relative to the paper-based document;
- decoding by the sensing device at least some of the coded data to form indicating data indicative of the identity of the field of the paper-based document containing the coded data and at least one of a position and a movement of the sensing device relative to the paper-based document;
- receiving in a server the indicating data from the sensing device;
- processing the indicating data using a recognizer residing on the server to produce intermediate format data;
- receiving the intermediate format data in an application; decoding the intermediate format data by the application into computer-readable format data using context information associated with the paper-based document. Other aspects are also disclosed.
- The present invention should become apparent from the following description, which is given by way of example only, of a preferred but non-limiting embodiment thereof, described in connection with the accompanying figures.
-
FIG. 1 (prior art) illustrates a distributed system architecture; -
FIG. 2 (prior art) illustrates a flow chart of basic pattern recognition steps; -
FIG. 3 illustrates an example processing system able to be used as a server to house a recognizer, according to a particular embodiment of the present invention; -
FIG. 4 illustrates an example distributed recognition system, according to a particular embodiment of the present invention; -
FIG. 5 illustrates an example of ambiguous handwriting input for “clog”/“dog”; -
FIG. 6 illustrates an example of ambiguous handwriting input for “tile”/“lite”; -
FIG. 7 illustrates an example recognition scenario, according to a particular embodiment of the present invention; -
FIG. 8 illustrates an example recognizer selection scenario, according to a particular embodiment of the present invention; -
FIG. 9 illustrates an example recognizer training scenario, according to a particular embodiment of the present invention; -
FIG. 10 illustrates an example recognizer registration scenario, according to a particular embodiment of the present invention. - The following modes, given by way of example only, are described in order to provide a more precise understanding of the subject matter of the present invention.
- A particular embodiment of the present invention can be realised using a processing system, an example of which is shown in
FIG. 3 . In particular, theprocessing system 300 generally includes at least oneprocessor 302, or processing unit or plurality of processors,memory 304 and at least oneoutput device 308, coupled together via a bus or group ofbuses 310. At least onestorage device 314 which houses at least onedatabase 316 can also be provided, which may be remote and accessed via a network. Thememory 304 can be any form of memory device, for example, volatile or non-volatile memory, solid state storage devices, magnetic devices, etc. Theprocessor 302 could include more than one distinct processing device, for example to handle different functions within theprocessing system 300. -
Input device 306, for example a pen-based input device or a microphone, is normally remote to thesystem 300.Input device 306 is used by a user to generatenatural language data 318 which is preferably transmitted over network 307 tosystem 300 for processing.Output device 308 produces or generatesintermediate format data 320, for example for transmission over a network, to be transmitted toapplication 324, which could be remote or local to thesystem 300. Thestorage device 314 can be any form of data or information storage means, for example, volatile or non-volatile memory, solid state storage devices, magnetic devices, etc. - In use, the
processing system 300 may be a server and is adapted to allow data or information to be stored in and/or retrieved from, via wired or wireless communication means, the at least onedatabase 316, which may be remote and accessed via a further network. Theprocessor 302 receivesnatural language data 318 frominput device 306, preferably via network 307, and outputsintermediate format data 320 by utilisingoutput device 308, for example a network interface. Theapplication 324 may return decoded data to the processing system. Theapplication 324 may cause information to be printed, for example on a Netpage™ printer, at a user's location. More than oneinput device 306 can be provided. It should be appreciated that theprocessing system 300 may be any form of terminal, server, specialised hardware, or the like. Theprocessing system 300 may be a part of a networked communications system. Also, theapplication 324 may initiate transfer ofnatural language data 318 from theinput device 306 toserver 300. - In a particular embodiment, the
server 300 is part of a system for computer-based recognition of natural language data, the system implemented on a network and comprising: theinput device 306 to obtain natural language data;server 300 to receive thenatural language data 318 via a network 307; a recognizer residing on theserver 300 to process, inprocessor 302, thenatural language data 318 to produceintermediate format data 320; and, anapplication 324 to receive theintermediate format data 320 and to decode theintermediate format data 320 into computer-readable format data using context information associated with theapplication 324. - The following example provides a more detailed discussion of a particular embodiment of the present invention. The example is intended to be merely illustrative and not limiting to the scope of the present invention.
- In a particular preferred embodiment, the present invention is configured to work with the Netpage™ networked computer system, a detailed description of which is given in the applicant's co-pending applications, including in particular, PCT Publication No. WO0242989 entitled “Sensing Device” filed 30 May 2002, PCT Publication No. WO0242894 entitled “Interactive Printer” filed 30 May 2002, PCT Publication No. WO0214075 “Interface Surface Printer Using Invisible Ink” filed 21 Feb. 2002, PCT Publication No. WO0242950 “Apparatus For Interaction With A Network Computer System” filed 30 May 2002, and PCT Publication No. WO03034276 entitled “Digital Ink Database Searching Using Handwriting Feature Synthesis” filed 24 Apr. 2003.
- It will be appreciated that not every implementation will necessarily embody all or even most of the specific details and extensions described in these applications in relation to the basic system. However, the system is described in its most complete form to assist in understanding the context in which the preferred embodiments and aspects of the present invention operate.
- In brief summary, the preferred form of the Netpage system provides an interactive paper-based interface to online information by utilizing pages of invisibly coded paper and an optically imaging pen. Each page generated by the Netpage system is uniquely identified and stored on a network server, and all user interaction with the paper using the Netpage pen is captured, interpreted, and stored. Digital printing technology facilitates the on-demand printing of Netpage documents, allowing interactive applications to be developed. The Netpage printer, pen, and network infrastructure provide a paper-based alternative to traditional screen-based applications and online publishing services, and supports user-interface functionality such as hypertext navigation and form input.
- Typically, a printer receives a document from a publisher or application provider via a broadband connection, which is printed with an invisible pattern of infrared tags that each encodes the location of the tag on the page and a unique page identifier. As a user writes on the page, the imaging pen decodes these tags and converts the motion of the pen into digital ink. The digital ink is transmitted over a wireless channel to a relay base station, and then sent to the network for processing and storage. The system uses a stored description of the page to interpret the digital ink, and performs the requested actions by interacting with an application.
- Applications provide content to the user by publishing documents, and process the digital ink interactions submitted by the user. Typically, an application generates one or more interactive pages in response to user input, which are transmitted to the network to be stored, rendered, and finally printed as output to the user. The Netpage system allows sophisticated applications to be developed by providing services for document publishing, rendering, and delivery, authenticated transactions and secure payments, handwriting recognition and digital ink searching, and user validation using biometric techniques such as signature verification.
- Distributed Pattern Recognition
- An example architecture for a distributed
pattern recognition system 400 is depicted inFIG. 4 . In the example, asignal 410 is recorded by aninput device 415 at aclient layer 420 and transmitted over a network to a server (network layer 430) for recognition by arecognizer 440, with theintermediate results 445 transmitted back to theclient layer 420 or athird party application 450 on anapplication layer 455 for interpretation and processing. One advantage of this approach is thatclient devices 415 and distributedapplications 450 do not require the significant computing resources commonly needed to perform natural language pattern recognition, and the network servers that perform the recognition are not subject to the resource constraints that are inherent in many client devices 415 (e.g. mobile phones, personal-digital assistants, imaging pens, etc.). As a result, network servers are able to use extremely processor- and/or memory-intensive techniques to improve recognition accuracy, and can use hardware optimised to perform the specific recognition task. - Performing pattern recognition on a centralized server (e.g. processing system 300) also offers an advantage to pattern-recognition systems that employ user-specific adaptation to achieve higher recognition rates. For example, some handwriting recognition techniques develop a handwriting model for each user of the system based on previous recognition results, which is then used to improve the future accuracy of the system for that user (see for example L. Schomaker, H. Teulings, E. Helsper, and G. Abbink, “Adaptive Recognition Of Online, Cursive Handwriting”, Proceedings of the Sixth International Conference on Handwriting and Drawing. Paris, July, 4-7 Telecom, (pp. 19-21), 1993 and S. Connell and A. K. Jain, “Writer Adaptation of Online Handwritten Models,” Proc. 5th International Conference on Document Analysis and Recognition, Bangalore, India, pp. 434-437, September 1999).
- This adaptation is more effective if a single server, or set of servers, performs all recognition for a user (rather than a large number of individual applications each performing their own recognition), since the server is able to perform adaptation based on the input generated by all applications. In addition to this, centralized server-based pattern recognition simplifies the management of the
recognition system 400 by allowing recognizers to be reconfigured and upgraded without interaction with the distributedclient devices 415 andapplications 450, and allows training and test data to be easily collected. - However, the information required to perform the context processing stage of a pattern recognition system is generally application specific and is often very large (e.g. entries in a large application-specific database), making it impractical to transmit the context information to a centralized server for processing. A solution to this problem is to use a mechanism for distributed recognition as depicted in
FIG. 4 . When a user generates a signal (i.e. natural language data) 410 to be recognized and processed by an application, thesignal 410 is submitted to a distributed server for processing. The server performs processing steps such as pre-processing, segmentation, and classification (seeFIG. 2 ), but does not use a context model to decode the result (or only performs partial decoding as described in the following discussion). Rather, the intermediate recognition results (i.e. intermediate format data) are returned or sent to the application allowing the application to apply any arbitrarily complex and domain-specific context processing to decode the signal. - Symbol DAG
- One method of returning the intermediate recognition results (i.e. intermediate format data) to an application is to use a symbol DAG (Directed Acyclic Graph), which is a generic data structure that contains symbol and associated scores as vertices, and valid transitions between symbols as edges. The structure can be implemented as a two-dimensional array of elements, each of which defines the output generated by the pattern classifier for a single segment of the signal and the associated valid transitions for that segment. This structure represents all the potential recognition alternatives that may be derived from the input signal based on the results of the classifier. The application uses this structure, in combination with a context model, to decode the input signal.
- The symbol DAG is equivalent to a matrix where each column contains the results of the classification of a single segment of the input signal. Each element in the column represents the probability that the classified segment is a particular symbol, and includes an offset that indicates the next possible segment (column) in the input signal that can follow this symbol. Thus, the matrix represents all the possible decoding paths based on the output of the pattern classifier. These paths and associated classification scores can be combined with a context model to fully decode the input signal.
- Note that the symbol DAG is applicable in any pattern recognition task where a sequence of classification results is decoded using a context or set of constraints. The symbols contained in the symbol DAG may be any primitive element that is generated as the output of a pattern classifier, including the output from a time-series classifier. Examples of such recognition systems include handwriting and speech recognition, protein sequencing (see A. C. Camproux, P. Tuffery, S. Hazout, “Hidden Markov Model Approach For Identifying The Modular Framework Of The Protein Backbone”, Protein engineering, 12(12), pp. 1063, December 1999), image processing and computer vision (see Y. He, A. Kundu, “2-D Shape Classification Using Hidden Markov Model”, IEEE Transactions on Pattern Analysis, 13(11), November 1991), and econometrics (see T. Ryden, T. Terasvirta, S. Asbrink, “Stylized Facts of Daily Return Series and the Hidden Markov Model”, Journal of Applied Econometrics, 13(3), pp. 217, May 1998).
- Symbol DAG Example
- As an example, Table 1 shows a symbol DAG that represents the output from a handwritten character recognizer generated by the ambiguous text given in
FIG. 5 . In this example, the recognizer has found two possible character segmentation arrangements, as depicted by the two rows in the symbol DAG. Note that in the examples, the symbol scores are given as probabilities; however, an actual implementation may typically use log-probabilities (i.e. the base-10 logarithm of the probability result) to improve the performance of context processing and to avoid overflow and underflow problems that occur when multiplying probabilities using finite precision floating-point operations. - To decode the alternatives, the context processor starts with the first entry in the DAG (i.e. the character ‘c’). The score for this entry is added to the accumulated total (since log-probabilities are added rather than multiplied), and processing moves to the column given by the offset value in the entry (in this example, column 1). In column 1, two alternatives exist (i.e. “cl” or “cb”), and the scores for these alternatives are found by adding the scores to the previous total. The decoding continues until the end of the DAG is reached. Similarly, the second entry in column 0 (i.e. the character ‘d’) is decoded; note however, that column 1 is skipped in this traversal of the DAG, as indicated by the offset value of 2 in the character score entry. This is due to the letter ‘d’ being constructed using two strokes, and thus the recognition of the letters ‘l’ and ‘b’ cannot be valid in this alternative. Thus, the potential decoding alternatives in this example are:
-
c log=0.7*0.8*1.0*1.0=0.56 -
cbg=0.7*0.2*1.0=0.14 -
dog=0.3*1.0*1.0=0.30 - These values can now be combined with a language model or other contextual information to select the most likely word.
-
TABLE 1 Example DAG for “clog”/“dog” ambiguity 0 1 2 3 Character c l o g Offset 1 2 3 0 Score 0.7 0.8 1.0 1.0 Character d b Offset 2 3 Score 0.3 0.2 - The DAG structure must ensure that strokes are assigned to an individual letter only once. To do this, alternate paths must be defined to ensure that if a stroke is assigned to a letter, no subsequent letter may use that stroke in its construction. An example of this is given in
FIG. 6 , with the derived DAG depicted in Table 2. In this example, the short, horizontal marks can potentially be recognized as crossbar elements of a letter ‘t’, or diacritical marks for the letter ‘i’. However, if a marking is used as a crossbar, it cannot subsequently be used as a diacritical. The potential decoding alternatives in this example are: -
tile=0.6*1.0*0.6*1.0=0.36 -
tite=0.6*1.0*1.0*1.0=0.60 -
lite=0.4*1.0*1.0*1.0=0.40 - These values can now be combined with a language model to select the most likely word.
-
TABLE 2 Example DAG for “lite”/“tile” ambiguity 0 1 2 3 4 5 Character t i i t l e Offset 1 4 3 5 5 — Score 0.6 1.0 1.0 1.0 0.6 1.0 Character l t Offset 2 5 Score 0.4 0.4 - Additionally, the character value of a DAG entry can be set to zero, indicating a NUL character (i.e. a character that does not change the text, but will modify the text probability). This allows word break positions (i.e. spaces) to be modeled as a SPACE/NUL pair, indicating that there is a certain probability that a space appears at that point in the DAG. For example:
-
TABLE 3 Example DAG for SPACE/NUL pair 0 1 2 Character a NUL b Offset 1 1 — Score 1.0 0.6 1.0 Character SPACE Offset 1 Score 0.4 - The potential decoding alternatives in this example are:
-
ab=1.0*0.6*1.0=0.6 -
a b=1.0*0.4*1.0=0.4 - Distributed Recognizer Management
- Referring to
FIGS. 7 and 8 , a distributedrecognition system 700 may support a number ofdifferent recognizers 440 that are controlled by a distributed recognition management system orrecognition manager 710. Theserecognizers 440 can include systems capable of supporting different classes of recognition, such as different languages, dialects, or accents, or cursive or boxed input for handwriting systems. When anapplication 450 requires a recognition task to be performed, theapplication 450first queries 720 therecognition manager 710 to find arecognizer 440 that matches the parameters of the input to be recognized (as depicted inFIG. 8 ). Therecognition manager 710 then queries 730 each recognizer 440 to find a recognizer that supports the parameters specified by theapplication 450. When arecognizer 440 indicates support 740 (as opposed to nosupport 750 fromrecognizer 440 a inFIG. 8 ) for the specified parameter set, the enumeration ends and the selected recognizer 440 (in the case ofFIG. 8 recognizer 440 b) is passed 760 to theapplication 450. Note that theindividual recognizers 440 do not need to be centralized and may be distributed throughout thesystem 700, since therecognition manager 710 acts as a controller for the set ofrecognizers 440. Theapplication 450 can then request processing by the selected recognizer by passing or directing 770 the signal and parameters to the selectedrecognizer 440.Intermediate format data 445, i.e. a symbol lattice, is returned to theapplication 450 and theapplication 450 can return aresponse 780 to theinput device 415. - User-Specific Dictionaries
- Distributed recognition systems can also support user dictionaries, which are user-specific word lists (and possibly associated a-priori probabilities) that include words that a user writes frequently but which are unlikely to appear in a standard dictionary (examples include company names, work or personal interest specific terms, etc.). User dictionaries can be stored and managed centrally so that words added to the dictionary when using one application are available to all applications for context processing. Obviously, applications can manage and use their own local user-specific dictionaries if required, since they have full control over context decoding.
- When an application requires the recognition of a signal that may contain words found in the user dictionary (e.g. standard handwritten text input such as the subject line of an e-mail or an arbitrary voice message), the centralized recognition system generates the usual intermediate recognition results to be returned to the application for context decoding. However, in addition to this it decodes the intermediate results using the user-dictionary as a language model, the result of which is also returned to the application. These two intermediate results structures can be combined by the application during its context decoding to generate a final decoding that includes the user-specific dictionary information.
- User-Specific Training
- Distributed recognition systems may also support user-specific training for a
recognizer 440, as depicted inFIG. 9 . The data generated by a user-specific recognition training application is submitted 910 to thecentralized recognition manager 710, which stores 920 the data in adatabase 930. Therecognition manager 710 then enumerates allrecognizers 440 to determine if they support the data format as defined by the parameters associated with the training data, and if so (True signal 940), submits thetraining data 950 to therecognizer 440 for user-specific training - When an existing recognizer is upgraded or a new recognizer is added to the system, the
recognition manager 710 queries 1010 thetraining database 930 to determine if anytraining data 1020 of the format required by therecognizer 440 exists. If so, thetraining data 1020 is submitted to the newly registeredrecognizer 440 for processing, as depicted inFIG. 10 . - The invention may also be said to broadly consist in the parts, elements and features referred to or indicated herein, individually or collectively, in any or all combinations of two or more of the parts, elements or features, and wherein specific integers are mentioned herein which have known equivalents in the art to which the invention relates, such known equivalents are deemed to be incorporated herein as if individually set forth.
- Although a preferred embodiment has been described in detail, it should be understood that various changes, substitutions, and alterations can be made by one of ordinary skill in the art without departing from the scope of the present invention. We claim:
Claims (7)
1. A method of recognising digital ink input by a user into a computer-based digital ink recognition system, the user interacting with a paper-based document, the paper-based document having disposed thereon coded data indicative of a particular field of the paper-based document and of at least one reference point of the paper-based document, the method including the steps of:
capturing by an image sensor in a sensing device images of at least some of the coded data when the sensing device is placed in an operative position relative to the paper-based document;
decoding by the sensing device at least some of the coded data to form indicating data indicative of the identity of the field of the paper-based document containing the coded data and at least one of a position and a movement of the sensing device relative to the paper-based document;
receiving in a server the indicating data from the sensing device;
processing the indicating data using a recognizer residing on the server to produce intermediate format data;
receiving the intermediate format data in an application;
decoding the intermediate format data by the application into computer-readable format data using context information associated with the paper-based document.
2. The method as claimed in claim 1 , wherein the particular field of the paper-based document is associated with at least one zone of the paper-based document, and the method includes identifying the context information from the at least one zone.
3. The method as claimed in claim 1 , wherein the intermediate format data is a Directed Acyclic Graph (DAG) data structure.
4. The method as claimed in claim 3 , wherein the DAG data structure is a matrix containing the processing results of segments of the indicating data.
5. The method as claimed in claim 1 , wherein the intermediate format data includes segmented time-series classifier data.
6. The method as claimed in claim 1 , wherein the context information is a user dictionary.
7. The method as claimed in claim 1 , wherein the recognizer is trained for a specific user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/691,725 US20100125451A1 (en) | 2003-08-15 | 2010-01-21 | Natural Language Recognition Using Context Information |
Applications Claiming Priority (7)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2003904351 | 2003-08-15 | ||
AU2003904351A AU2003904351A0 (en) | 2003-08-15 | Systems, methods and apparatus (NPW013) | |
AU2003904350 | 2003-08-15 | ||
AU2003904350 | 2003-08-15 | ||
PCT/AU2004/001088 WO2005017767A1 (en) | 2003-08-15 | 2004-08-16 | Natural language recognition using distributed processing |
US10/510,392 US7660466B2 (en) | 2003-08-15 | 2004-08-16 | Natural language recognition using distributed processing |
US12/691,725 US20100125451A1 (en) | 2003-08-15 | 2010-01-21 | Natural Language Recognition Using Context Information |
Related Parent Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/AU2004/001088 Continuation WO2005017767A1 (en) | 2003-08-15 | 2004-08-16 | Natural language recognition using distributed processing |
US10/510,392 Continuation US7660466B2 (en) | 2003-08-15 | 2004-08-16 | Natural language recognition using distributed processing |
Publications (1)
Publication Number | Publication Date |
---|---|
US20100125451A1 true US20100125451A1 (en) | 2010-05-20 |
Family
ID=34137114
Family Applications (5)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/510,391 Abandoned US20060277159A1 (en) | 2003-08-15 | 2004-08-16 | Accuracy in searching digital ink |
US10/510,392 Expired - Fee Related US7660466B2 (en) | 2003-08-15 | 2004-08-16 | Natural language recognition using distributed processing |
US10/919,261 Abandoned US20050038644A1 (en) | 2003-08-15 | 2004-08-17 | Natural language recognition using distributed processing |
US12/691,725 Abandoned US20100125451A1 (en) | 2003-08-15 | 2010-01-21 | Natural Language Recognition Using Context Information |
US13/188,366 Abandoned US20110276596A1 (en) | 2003-08-15 | 2011-07-21 | System for interpeting digital ink |
Family Applications Before (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/510,391 Abandoned US20060277159A1 (en) | 2003-08-15 | 2004-08-16 | Accuracy in searching digital ink |
US10/510,392 Expired - Fee Related US7660466B2 (en) | 2003-08-15 | 2004-08-16 | Natural language recognition using distributed processing |
US10/919,261 Abandoned US20050038644A1 (en) | 2003-08-15 | 2004-08-17 | Natural language recognition using distributed processing |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/188,366 Abandoned US20110276596A1 (en) | 2003-08-15 | 2011-07-21 | System for interpeting digital ink |
Country Status (4)
Country | Link |
---|---|
US (5) | US20060277159A1 (en) |
EP (2) | EP1661028A1 (en) |
CA (2) | CA2529037A1 (en) |
WO (2) | WO2005017767A1 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100030560A1 (en) * | 2006-03-23 | 2010-02-04 | Nec Corporation | Speech recognition system, speech recognition method, and speech recognition program |
US20130136316A1 (en) * | 2011-11-30 | 2013-05-30 | Nokia Corporation | Method and apparatus for providing collaborative recognition using media segments |
US20130185054A1 (en) * | 2012-01-17 | 2013-07-18 | Google Inc. | Techniques for inserting diacritical marks to text input via a user device |
US20150302243A1 (en) * | 2014-04-18 | 2015-10-22 | Xerox Corporation | Distance based binary classifier of handwritten words |
Families Citing this family (51)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7155061B2 (en) * | 2000-08-22 | 2006-12-26 | Microsoft Corporation | Method and system for searching for words and phrases in active and stored ink word documents |
US20060277159A1 (en) * | 2003-08-15 | 2006-12-07 | Napper Jonathon L | Accuracy in searching digital ink |
US8232979B2 (en) | 2005-05-25 | 2012-07-31 | The Invention Science Fund I, Llc | Performing an action with respect to hand-formed expression |
US8340476B2 (en) | 2005-03-18 | 2012-12-25 | The Invention Science Fund I, Llc | Electronic acquisition of a hand formed expression and a context of the expression |
US7809215B2 (en) | 2006-10-11 | 2010-10-05 | The Invention Science Fund I, Llc | Contextual information encoded in a formed expression |
US7672512B2 (en) | 2005-03-18 | 2010-03-02 | Searete Llc | Forms for completion with an electronic writing device |
US7873243B2 (en) | 2005-03-18 | 2011-01-18 | The Invention Science Fund I, Llc | Decoding digital information included in a hand-formed expression |
US8229252B2 (en) | 2005-03-18 | 2012-07-24 | The Invention Science Fund I, Llc | Electronic association of a user expression and a context of the expression |
US8823636B2 (en) | 2005-03-18 | 2014-09-02 | The Invention Science Fund I, Llc | Including environmental information in a manual expression |
US20060212430A1 (en) | 2005-03-18 | 2006-09-21 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Outputting a saved hand-formed expression |
US8787706B2 (en) | 2005-03-18 | 2014-07-22 | The Invention Science Fund I, Llc | Acquisition of a user expression and an environment of the expression |
US8290313B2 (en) * | 2005-03-18 | 2012-10-16 | The Invention Science Fund I, Llc | Electronic acquisition of a hand formed expression and a context of the expression |
WO2006123575A1 (en) * | 2005-05-19 | 2006-11-23 | Kenji Yoshida | Audio information recording device |
US7965275B1 (en) * | 2006-01-13 | 2011-06-21 | Intuit Inc. | User interface for lenient exception feedback |
PT1994012E (en) * | 2006-02-10 | 2010-01-18 | Janssen Pharmaceutica Nv | Novel tricyclic dihydropyrazines as potassium channel openers |
EP1858005A1 (en) * | 2006-05-19 | 2007-11-21 | Texthelp Systems Limited | Streaming speech with synchronized highlighting generated by a server |
US8255216B2 (en) * | 2006-10-30 | 2012-08-28 | Nuance Communications, Inc. | Speech recognition of character sequences |
US7823138B2 (en) * | 2006-11-14 | 2010-10-26 | Microsoft Corporation | Distributed testing for computing features |
KR100897554B1 (en) * | 2007-02-21 | 2009-05-15 | 삼성전자주식회사 | Distributed speech recognition sytem and method and terminal for distributed speech recognition |
US20080294652A1 (en) * | 2007-05-21 | 2008-11-27 | Microsoft Corporation | Personalized Identification Of System Resources |
US8041120B2 (en) * | 2007-06-26 | 2011-10-18 | Microsoft Corporation | Unified digital ink recognition |
US8094939B2 (en) * | 2007-06-26 | 2012-01-10 | Microsoft Corporation | Digital ink-based search |
US8315482B2 (en) * | 2007-06-26 | 2012-11-20 | Microsoft Corporation | Integrated platform for user input of digital ink |
US8229225B2 (en) * | 2008-05-06 | 2012-07-24 | Wu Yingchao | Candidate selection method for handwriting input |
US8266078B2 (en) * | 2009-02-06 | 2012-09-11 | Microsoft Corporation | Platform for learning based recognition research |
US8423353B2 (en) * | 2009-03-25 | 2013-04-16 | Microsoft Corporation | Sharable distributed dictionary for applications |
CN101853297A (en) * | 2010-05-28 | 2010-10-06 | 英华达(南昌)科技有限公司 | Method for fast obtaining expected image in electronic equipment |
WO2012125753A2 (en) * | 2011-03-14 | 2012-09-20 | Amgine Technologies, Inc. | Processing and fulfilling natural language travel requests |
US11763212B2 (en) | 2011-03-14 | 2023-09-19 | Amgine Technologies (Us), Inc. | Artificially intelligent computing engine for travel itinerary resolutions |
US9659099B2 (en) | 2011-03-14 | 2017-05-23 | Amgine Technologies (Us), Inc. | Translation of user requests into itinerary solutions |
WO2013001146A2 (en) * | 2011-06-30 | 2013-01-03 | Nokia Corporation | Method and apparatus for real-time processing of data items |
US9026428B2 (en) * | 2012-10-15 | 2015-05-05 | Nuance Communications, Inc. | Text/character input system, such as for use with touch screens on mobile phones |
CA2944652A1 (en) | 2014-04-01 | 2015-10-08 | Amgine Technologies (Us), Inc. | Inference model for traveler classification |
US10203933B2 (en) | 2014-11-06 | 2019-02-12 | Microsoft Technology Licensing, Llc | Context-based command surfacing |
US9646611B2 (en) * | 2014-11-06 | 2017-05-09 | Microsoft Technology Licensing, Llc | Context-based actions |
CN105740267A (en) * | 2014-12-10 | 2016-07-06 | 北大方正集团有限公司 | PDF (Portable Document Format) file processing method and apparatus |
EP3279774B1 (en) | 2015-03-31 | 2021-02-24 | Wacom Co., Ltd. | Ink file output method, output device and program |
US11049047B2 (en) | 2015-06-25 | 2021-06-29 | Amgine Technologies (Us), Inc. | Multiattribute travel booking platform |
US10041803B2 (en) | 2015-06-18 | 2018-08-07 | Amgine Technologies (Us), Inc. | Scoring system for travel planning |
US11941552B2 (en) | 2015-06-25 | 2024-03-26 | Amgine Technologies (Us), Inc. | Travel booking platform with multiattribute portfolio evaluation |
US10210383B2 (en) | 2015-09-03 | 2019-02-19 | Microsoft Technology Licensing, Llc | Interacting with an assistant component based on captured stroke information |
US10387034B2 (en) | 2015-09-03 | 2019-08-20 | Microsoft Technology Licensing, Llc | Modifying captured stroke information into an actionable form |
US9858923B2 (en) * | 2015-09-24 | 2018-01-02 | Intel Corporation | Dynamic adaptation of language models and semantic tracking for automatic speech recognition |
US10228775B2 (en) * | 2016-01-22 | 2019-03-12 | Microsoft Technology Licensing, Llc | Cross application digital ink repository |
JP2018112839A (en) * | 2017-01-10 | 2018-07-19 | 富士通株式会社 | Image processing program, image recognition program, image processing device, image recognition device, image recognition method, and image processing method |
US10535342B2 (en) * | 2017-04-10 | 2020-01-14 | Microsoft Technology Licensing, Llc | Automatic learning of language models |
US10452449B1 (en) * | 2017-05-01 | 2019-10-22 | Ambarella, Inc. | Scheduler for vector processing operator allocation |
JP6883471B2 (en) * | 2017-05-11 | 2021-06-09 | オリンパス株式会社 | Sound collecting device, sound collecting method, sound collecting program, dictation method and information processing device |
US10970476B2 (en) * | 2017-05-17 | 2021-04-06 | Microsoft Technology Licensing, Llc | Augmenting digital ink strokes |
US11176361B2 (en) * | 2018-06-21 | 2021-11-16 | Raytheon Company | Handwriting detector, extractor, and language classifier |
US11113469B2 (en) | 2019-03-27 | 2021-09-07 | International Business Machines Corporation | Natural language processing matrices |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5455872A (en) * | 1993-04-26 | 1995-10-03 | International Business Machines Corporation | System and method for enhanced character recogngition accuracy by adaptive probability weighting |
US5546538A (en) * | 1993-12-14 | 1996-08-13 | Intel Corporation | System for processing handwriting written by user of portable computer by server or processing by the computer when the computer no longer communicate with server |
US5870706A (en) * | 1996-04-10 | 1999-02-09 | Lucent Technologies, Inc. | Method and apparatus for an improved language recognition system |
US5982928A (en) * | 1994-06-21 | 1999-11-09 | Canon Kabushiki Kaisha | Character recognizing apparatus and method of controlling the same |
US6216013B1 (en) * | 1994-03-10 | 2001-04-10 | Cable & Wireless Plc | Communication system with handset for distributed processing |
US20010012401A1 (en) * | 1998-07-22 | 2001-08-09 | William Arpad Nagy | Process for utilizing external handwriting recognition for personal data assistants |
US20020107885A1 (en) * | 2001-02-01 | 2002-08-08 | Advanced Digital Systems, Inc. | System, computer program product, and method for capturing and processing form data |
US6456974B1 (en) * | 1997-01-06 | 2002-09-24 | Texas Instruments Incorporated | System and method for adding speech recognition capabilities to java |
US6456740B1 (en) * | 1999-07-26 | 2002-09-24 | International Business Machines Corporation | System and method for identifying form type in a handwriting recognition based form completion system |
US20040064783A1 (en) * | 2002-09-30 | 2004-04-01 | Braun John F. | Method and system for remote form completion |
US20040126017A1 (en) * | 2002-12-30 | 2004-07-01 | Giovanni Seni | Grammar-determined handwriting recognition |
US20050013487A1 (en) * | 2001-01-24 | 2005-01-20 | Advanced Digital Systems, Inc. | System, computer software product and method for transmitting and processing handwritten data |
US20070104372A1 (en) * | 2002-10-31 | 2007-05-10 | Microsoft Corporation | Active embedded interaction coding |
US7289685B1 (en) * | 2002-04-04 | 2007-10-30 | Ricoh Co., Ltd. | Paper based method for collecting digital data |
US7336827B2 (en) * | 2000-11-08 | 2008-02-26 | New York University | System, process and software arrangement for recognizing handwritten characters |
US7660466B2 (en) * | 2003-08-15 | 2010-02-09 | Silverbrook Research Pty Ltd | Natural language recognition using distributed processing |
Family Cites Families (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4864618A (en) | 1986-11-26 | 1989-09-05 | Wright Technologies, L.P. | Automated transaction system with modular printhead having print authentication feature |
US5051736A (en) | 1989-06-28 | 1991-09-24 | International Business Machines Corporation | Optical stylus and passive digitizing tablet data input system |
US5477012A (en) * | 1992-04-03 | 1995-12-19 | Sekendur; Oral F. | Optical position determination |
US5852434A (en) | 1992-04-03 | 1998-12-22 | Sekendur; Oral F. | Absolute optical position determination |
JPH07117993B2 (en) * | 1992-04-29 | 1995-12-18 | 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 | A User-Specific Prototype Set Generation Method for Handwritten Character Recognition |
US5687254A (en) * | 1994-06-06 | 1997-11-11 | Xerox Corporation | Searching and Matching unrecognized handwriting |
DE69428527T2 (en) * | 1994-07-04 | 2002-05-08 | Hewlett Packard Co | Kritzlervergleich |
US5652412A (en) | 1994-07-11 | 1997-07-29 | Sia Technology Corp. | Pen and paper information recording system |
US5661506A (en) | 1994-11-10 | 1997-08-26 | Sia Technology Corporation | Pen and paper information recording system using an imaging pen |
US6081261A (en) | 1995-11-01 | 2000-06-27 | Ricoh Corporation | Manual entry interactive paper and electronic document handling and processing system |
US6055333A (en) * | 1995-12-28 | 2000-04-25 | Motorola, Inc. | Handwriting recognition method and apparatus having multiple selectable dictionaries |
US5832474A (en) * | 1996-02-26 | 1998-11-03 | Matsushita Electric Industrial Co., Ltd. | Document search and retrieval system with partial match searching of user-drawn annotations |
US5692073A (en) * | 1996-05-03 | 1997-11-25 | Xerox Corporation | Formless forms and paper web using a reference-based mark extraction technique |
JP4098880B2 (en) * | 1997-06-06 | 2008-06-11 | 松下電器産業株式会社 | Information retrieval device |
US6518950B1 (en) | 1997-10-07 | 2003-02-11 | Interval Research Corporation | Methods and systems for providing human/computer interfaces |
WO1999050736A1 (en) | 1998-04-01 | 1999-10-07 | Xerox Corporation | Paper indexing of recordings |
US6964374B1 (en) * | 1998-10-02 | 2005-11-15 | Lucent Technologies Inc. | Retrieval and manipulation of electronically stored information via pointers embedded in the associated printed material |
US20030007018A1 (en) * | 2001-07-09 | 2003-01-09 | Giovanni Seni | Handwriting user interface for personal digital assistants and the like |
US7158678B2 (en) * | 2001-07-19 | 2007-01-02 | Motorola, Inc. | Text input method for personal digital assistants and the like |
AUPR824301A0 (en) * | 2001-10-15 | 2001-11-08 | Silverbrook Research Pty. Ltd. | Methods and systems (npw001) |
AUPS020302A0 (en) * | 2002-01-31 | 2002-02-21 | Silverbrook Research Pty. Ltd. | Methods and systems (npw007) |
US20030215145A1 (en) * | 2002-05-14 | 2003-11-20 | Microsoft Corporation | Classification analysis of freeform digital ink input |
US7227993B2 (en) * | 2003-01-27 | 2007-06-05 | Microsoft Corporation | Learning-based system and process for synthesizing cursive handwriting |
AU2003900865A0 (en) * | 2003-02-26 | 2003-03-13 | Silverbrook Research Pty Ltd | Methods, systems and apparatus (NPW010) |
US20050024690A1 (en) * | 2003-07-31 | 2005-02-03 | Picciotto Carl E. | Pen with tag reader and navigation system |
-
2004
- 2004-08-16 US US10/510,391 patent/US20060277159A1/en not_active Abandoned
- 2004-08-16 EP EP04761125A patent/EP1661028A1/en not_active Withdrawn
- 2004-08-16 EP EP04761124A patent/EP1665086A4/en not_active Withdrawn
- 2004-08-16 US US10/510,392 patent/US7660466B2/en not_active Expired - Fee Related
- 2004-08-16 WO PCT/AU2004/001088 patent/WO2005017767A1/en active Application Filing
- 2004-08-16 CA CA002529037A patent/CA2529037A1/en not_active Abandoned
- 2004-08-16 WO PCT/AU2004/001087 patent/WO2005017768A1/en active IP Right Grant
- 2004-08-16 CA CA002529040A patent/CA2529040A1/en not_active Abandoned
- 2004-08-17 US US10/919,261 patent/US20050038644A1/en not_active Abandoned
-
2010
- 2010-01-21 US US12/691,725 patent/US20100125451A1/en not_active Abandoned
-
2011
- 2011-07-21 US US13/188,366 patent/US20110276596A1/en not_active Abandoned
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5455872A (en) * | 1993-04-26 | 1995-10-03 | International Business Machines Corporation | System and method for enhanced character recogngition accuracy by adaptive probability weighting |
US5546538A (en) * | 1993-12-14 | 1996-08-13 | Intel Corporation | System for processing handwriting written by user of portable computer by server or processing by the computer when the computer no longer communicate with server |
US6216013B1 (en) * | 1994-03-10 | 2001-04-10 | Cable & Wireless Plc | Communication system with handset for distributed processing |
US5982928A (en) * | 1994-06-21 | 1999-11-09 | Canon Kabushiki Kaisha | Character recognizing apparatus and method of controlling the same |
US5870706A (en) * | 1996-04-10 | 1999-02-09 | Lucent Technologies, Inc. | Method and apparatus for an improved language recognition system |
US6456974B1 (en) * | 1997-01-06 | 2002-09-24 | Texas Instruments Incorporated | System and method for adding speech recognition capabilities to java |
US6343148B2 (en) * | 1998-07-22 | 2002-01-29 | International Business Machines Corporation | Process for utilizing external handwriting recognition for personal data assistants |
US20010012401A1 (en) * | 1998-07-22 | 2001-08-09 | William Arpad Nagy | Process for utilizing external handwriting recognition for personal data assistants |
US6456740B1 (en) * | 1999-07-26 | 2002-09-24 | International Business Machines Corporation | System and method for identifying form type in a handwriting recognition based form completion system |
US7336827B2 (en) * | 2000-11-08 | 2008-02-26 | New York University | System, process and software arrangement for recognizing handwritten characters |
US20050013487A1 (en) * | 2001-01-24 | 2005-01-20 | Advanced Digital Systems, Inc. | System, computer software product and method for transmitting and processing handwritten data |
US20020107885A1 (en) * | 2001-02-01 | 2002-08-08 | Advanced Digital Systems, Inc. | System, computer program product, and method for capturing and processing form data |
US7289685B1 (en) * | 2002-04-04 | 2007-10-30 | Ricoh Co., Ltd. | Paper based method for collecting digital data |
US20040064783A1 (en) * | 2002-09-30 | 2004-04-01 | Braun John F. | Method and system for remote form completion |
US20070104372A1 (en) * | 2002-10-31 | 2007-05-10 | Microsoft Corporation | Active embedded interaction coding |
US20040126017A1 (en) * | 2002-12-30 | 2004-07-01 | Giovanni Seni | Grammar-determined handwriting recognition |
US7660466B2 (en) * | 2003-08-15 | 2010-02-09 | Silverbrook Research Pty Ltd | Natural language recognition using distributed processing |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100030560A1 (en) * | 2006-03-23 | 2010-02-04 | Nec Corporation | Speech recognition system, speech recognition method, and speech recognition program |
US8781837B2 (en) * | 2006-03-23 | 2014-07-15 | Nec Corporation | Speech recognition system and method for plural applications |
US20130136316A1 (en) * | 2011-11-30 | 2013-05-30 | Nokia Corporation | Method and apparatus for providing collaborative recognition using media segments |
US9280708B2 (en) * | 2011-11-30 | 2016-03-08 | Nokia Technologies Oy | Method and apparatus for providing collaborative recognition using media segments |
US20130185054A1 (en) * | 2012-01-17 | 2013-07-18 | Google Inc. | Techniques for inserting diacritical marks to text input via a user device |
US8812302B2 (en) * | 2012-01-17 | 2014-08-19 | Google Inc. | Techniques for inserting diacritical marks to text input via a user device |
US20150302243A1 (en) * | 2014-04-18 | 2015-10-22 | Xerox Corporation | Distance based binary classifier of handwritten words |
US9361515B2 (en) * | 2014-04-18 | 2016-06-07 | Xerox Corporation | Distance based binary classifier of handwritten words |
Also Published As
Publication number | Publication date |
---|---|
US20110276596A1 (en) | 2011-11-10 |
US20060277159A1 (en) | 2006-12-07 |
EP1661028A1 (en) | 2006-05-31 |
CA2529037A1 (en) | 2005-02-24 |
US7660466B2 (en) | 2010-02-09 |
US20050038644A1 (en) | 2005-02-17 |
WO2005017768A1 (en) | 2005-02-24 |
EP1665086A4 (en) | 2009-09-02 |
EP1665086A1 (en) | 2006-06-07 |
US20060149549A1 (en) | 2006-07-06 |
CA2529040A1 (en) | 2005-02-24 |
WO2005017767A1 (en) | 2005-02-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7660466B2 (en) | Natural language recognition using distributed processing | |
Calvo-Zaragoza et al. | Handwritten music recognition for mensural notation with convolutional recurrent neural networks | |
CN1107283C (en) | Method and apparatus for character recognition of handwriting input | |
Hu et al. | Writer independent on-line handwriting recognition using an HMM approach | |
CN109887484B (en) | Dual learning-based voice recognition and voice synthesis method and device | |
JP3848319B2 (en) | Information processing method and information processing apparatus | |
US8504350B2 (en) | User-interactive automatic translation device and method for mobile device | |
US20060106610A1 (en) | Method of improving recognition accuracy in form-based data entry systems | |
CN1779783B (en) | Generic spelling mnemonics | |
US7536649B2 (en) | Apparatus, system, and server capable of effectively specifying information in document | |
CN101140617A (en) | Electronic equipments and text inputting method | |
Addis et al. | Printed ethiopic script recognition by using lstm networks | |
CN113469163B (en) | Medical information recording method and device based on intelligent paper pen | |
Calvo-Zaragoza et al. | Recognition of pen-based music notation with finite-state machines | |
Chowdhury et al. | A weighted finite-state transducer (WFST)-based language model for online Indic script handwriting recognition | |
CN112989839A (en) | Keyword feature-based intent recognition method and system embedded in language model | |
AU2004265700B2 (en) | Natural language recognition using distributed processing | |
CN114861669A (en) | Chinese entity linking method integrating pinyin information | |
Martin-Albo et al. | Multimodal computer-assisted transcription of text images at character-level interaction | |
Idziak et al. | Scalable handwritten text recognition system for lexicographic sources of under-resourced languages and alphabets | |
JP2009110204A (en) | Document processing apparatus, document processing system, document processing method, and document processing program | |
AU2003266850B2 (en) | Method of improving recognition accuracy in form-based data entry systems | |
Toselli et al. | Probabilistic Models for Handwritten Text | |
JP2022013032A (en) | Information processing device, control method, and program | |
Loudon et al. | A method for handwriting input and correction on smartphones |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: SILVERBROOK RESEARCH PTY LTD,AUSTRALIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:NAPPER, JONATHON LEIGH;LAPSTUN, PAUL;SILVERBROOK, KIA;REEL/FRAME:023829/0410 Effective date: 20040923 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |