CA2195178A1 - Document search and retrieval system with partial match searching of user-drawn annotations - Google Patents

Document search and retrieval system with partial match searching of user-drawn annotations

Info

Publication number
CA2195178A1
CA2195178A1 CA002195178A CA2195178A CA2195178A1 CA 2195178 A1 CA2195178 A1 CA 2195178A1 CA 002195178 A CA002195178 A CA 002195178A CA 2195178 A CA2195178 A CA 2195178A CA 2195178 A1 CA2195178 A1 CA 2195178A1
Authority
CA
Canada
Prior art keywords
user
data
stroke
document
drawn
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
Application number
CA002195178A
Other languages
French (fr)
Inventor
Daniel P. Lopresti
Yue Ma
Jian Zhou
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Panasonic Holdings Corp
Original Assignee
Matsushita Electric Industrial Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Matsushita Electric Industrial Co Ltd filed Critical Matsushita Electric Industrial Co Ltd
Publication of CA2195178A1 publication Critical patent/CA2195178A1/en
Abandoned legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/93Document management systems
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99932Access augmentation or optimizing
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99933Query processing, i.e. searching
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99933Query processing, i.e. searching
    • Y10S707/99936Pattern matching access

Abstract

The document browser for electronic filing systems supports pen-based markup and annotation. The user may electronically write notes anywhere on a page and then later search for those notes using the approximate ink matching (AIM) technique. The technique segments the user-drawn strokes, extracts and vector quantizes features contained in those strokes. An edit distance comparison technique is used to query the database, rendering the system capable of performing approximate or partial matches to achieve fuzzy search capability.

Description

. ` 219517~

DOCUMENT SEARCH AND RETRIEVAL SYSTEM WITH
PARTIAL MATCH SEARCHING OF USER-DRAWN ANNOTATIONS

Back~.GL~d and Summary of the Invention The present invention relates generally to database search and retrieval systems. More particularly, the invention relates to a document annotation, search and retrieval system that supports searchable user-drawn annotations. Using a digitizing pen or other suitable drawing device, the user electronically draws annotations that are electronically displayed on and stored with a selected document within the database. The search engine is able to locate the annotated document in response to a user-drawn query by a partial match searching technique. The partial match searching technique compares temporal and spatial components of the user-drawn annotations without requiring translation into alphanumeric characters. Thus the search engine works with all forms of user-drawn characters, symbols, pictures and the like.
The partial match searching technique works at two levels. First, in the "ink" data type domain (temporal and spatial components of user-drawn annotations), a fuzzy match between the query ink and the database ink allows user-drawn annotations to be located in the database, even though the user does not draw the annotation in precisely the same way in entering a query.
Second, the partial match (word spotting) technique can identify a portion of a user-drawn annotation, even though the entire annotation is not entered as the query. The preferred partial match searching technique handles both levels of approximate matching.
Traditional document storage databases rely on various indexing systems to allow the user to store and then later locate a document of interest. Conventionally, documents in the form of alphanumeric text can be directly searched using keyword searching techniques. Bitmapped images, scanned images and graphics are another matter. Conventionally bitmapped images, scanned images and graphics must first be indexed by adding alphanumeric numbers or keywords before those documents can be searched for and retrieved. Normally these index numbers and keywords are added by keyboard entry as alphanumeric text. Alternatively, optical character recognition (OCR) techniques can be used to convert bitmapped images of text into a form that may be directly searched using keyword searching techniques.
Although the use of alphanumeric text in search and retrieval systems works reliably in many database applications, there are many applications that are not well suited to document indexing and annotating by keyboard entry. The enterprise-wide document and image management system is a good example.
There is considerable interest today in document and image management systems that may be deployed through networking across an entire enterprise. Flexibility and ease of use are prime considerations. Use of existing office automation equipment, where possible, is also highly desirable. Thus, fax machines, photocopiers and flatbed scanners may be used as document input devices in a networked document storage and retrieval system. For example, an electronic image copy of a document may be captured and stored in a document database as a photocopy of the document is being made. Once stored in the database, a user connected to the database, as over a network, can view the document on-screen and can print a hard copy of the document using an attached printer. Such a document storage and retrieval system has the capacity to capture hundreds of thousands of documents that may be later shared with others on the network. Although these new systems promise a "paperless" office of the future, there is still considerable momentum behind the old-fashioned paper copy.
Heretofore the old-fashioned paper copy of a document is more useful to many, because it can be written on to add personal handwritten notes, underlining and other such user-drawn annotations. The difficulty with the old-fashioned paper copy is that these user-drawn annotations form no active part of the document database. Although it is possible to re-scan the document once annotations have been added, this unnecessarily enlarges the size of the document database and the annotations themselves form no part of the computer searchable indexing system.
The present invention represents a significant advance in document storage and retrieval systems. The invention permits user-drawn annotations to be readily incorporated into or associated with the stored document, without requiring duplication of the document. Significantly, the user annotations can be searched as part of a document retrieval query. Using a pen interface the user electronically makes one or more annotations on the displayed image of a stored document. These annotations become associated with the stored document and may be searched to later retrieve the document.
The system captures user-drawn annotations as a sequence or string of "ink"
strokes, capturing the precise (X,Y) position of the pen tip over time as the user writes or draws an annotation. Thus the ink data type captures not only the spatial position of the ink but also the temporal sequence over which the ink is applied as the user draws the annotation.
By facilitating the search and retrieval of hand-drawn annotations, the present invention becomes extremely powerful in multilingual applications. For example, the user can readily enter hand-drawn Kanji (Chinese or Japanese) and/or Arabic annotations without requiring a suitably programmed keyboard. This is a significant advantage over any system based on keyboard entry alone.
The electronic ink strokes are stored in association with the document image, allowing the user-drawn annotation to be displayed on the display screen, at the originally-drawn location, when the document is retrieved from the database for viewing. The document browser includes a document query tool for the user to enter annotation search requests. The query tool presents a window into which the user draws a query request using the pen. For example, the user can write the word "Important!" in the query window and the search engine will then search the document database for all occurrences that match the user's hand-drawn entry "Important!". The search engine does not require an exact match, rather it has the flexibility to identify multiple variations of the hand-drawn entry (fuzzy matching).

Furthermore, the search engine is able to search for a portion of the annotation in question. Thus the user could write "Important" and find all occurrences of the annotation "Important information."
The search engine performs ink stroke pattern matching that does not require a translation of the ink stroke into an alphanumeric character.
Indeed, the system works quite well with user-drawn symbols of any arbitrary design. Thus there is no need to rely on unreliable handwriting recognition algorithms. However, if desired, handwriting recognition algorithms can be performed in background to augment the system's searching capabilities. Use of handwriting recognition to augment system performance is applicable to annotations consisting of text.
Accordingly, in one aspect the invention provides a document search and retrieval system that employs a memory having a first data structure for storing document data and a second data structure for storing annotation data. The system also includes a user interface having a drawing tool for user input of stroke data corresponding to a user-drawn annotation.
The stroke data has spatial and temporal components. The user interface communicates with the second data structure to store the spatial and temporal components of the stroke data in association with a user-selected portion of the document data. In practice, the stroke data corresponding to a user-drawn annotation may be associated with a region on a page of a document.
The system further includes a search engine that communicates with the user interface to receive a user-drawn search query comprising stroke data. The search engine communicates with the second data structure for 21 95 1 7~

matching patterns in the spatia1 and temporal components of the search query with patterns in the spatial and temporal components of the user-drawn annotation. The search engine ranks at least a portion of the annotations in the database based on the search results and presents them to the user in the form of one or more hypotheses. Preferably, the system will return the search results to the user in decreasing order of "goodness."
The search engine then accesses the first data structure to select a portion of the document data that corresponds to the user-selected match hypothesis. In this way the page or other portion of the document data associated with the user-drawn annotation is retrieved for viewing by the user.
For a more complete understanding of the invention, its objects and advantages, reference may be had to the following specification and to the accompanying drawings.

Bri ef Descri pti on of the Drawi ngs Figure 1 is a block diagram illustrating an exemplary embodiment of the invention;
Figure 2 illustrates one possible document browser screen useful in understanding the annotation capabilities of the invention;
Figure 3 is a detailed view illustrating the operation of the annotation editing slider bar;
Figure 4 illustrates one possible user interface screen for inputting an annotation query in using the invention;

~ Figure 5 is a software block diagram of the search and retrieval system of the invention;
Figure 6 is a functional diagram illustrating the basic edit distance technique used by the preferred embodiment;
Figure 7 is another functional diagram illustrating how a partial match may be performed with the edit distance technique;
Figure 8 illustrates the manner in which a user-entered query will select multiple candidates, sorted on the basis of score;
Figure 9 is a diagram illustrating the partial match or word spotting functionality of the invention through English, Kanji and pictorial examples;
Figure 10 illustrates how line breaks have no impact on the ink search strategy of the presently preferred embodiment; and Figure 11 is a flowchart diagram illustrating the pen stroke classification using vector quantization according to the presently preferred embodiment.

Description of the Preferred Embodiment Referring to Figure 1, a network-based document storage and retrieval system is illustrated generally at 10. The illustrated system is merely one possible configuration. In Figure 1 the document database is diagrammatically illustrated at 12. It will be understood that the document database can take many forms. For example, the document database may be implemented as a file server 13, with digital documents being stored on a suitable read/write storage media such as hard disk 15. The file server and its associated storage media may form part of a computer network connected via a suitable communication transmission link such as illustrated generally at 14.
The network may also include one or more computer workstations, such as workstation 16 having monitor 18 and running a client document browser application 20. In Figure 2 the document browser application is shown as its display would appear on monitor 18. It will be understood that the browser software application is actually running on workstation 16 and that the display appearing on monitor 18 is produced by the running browser application.
The workstation 16 is provided with a drawing tool, such as a pen 22 and digitizing tablet 24. The pen and digitizing tablet is coupled through the user interface of the browser application 20, allowing the user to draw on the tablet with the pen and see the results appear as annotations on the document browser display screen.
Regarding the drawing tool, although a digitizing tablet and pen is illustrated here, alternate embodiments are possible. For example, a light pen could be used to draw directly on the monitor screen in lieu of the digitizing tablet and pen. Alternatively, a suitably programmed pen computer or personal digital assistant (PDA), such as the Apple Newton could be used.

2~95178 The browser application 20 running on workstation 16 communicates over the network 14 to retrieve and display documents stored in database 12.
As will be described, the user may interact with these documents using the drawing tools provided at the workstation.
There are a number of ways to input documents into the document database. Several options are illustrated in Figure 1. Digitized images of documents can be input from a number of sources including the fax machine 26, the photocopy machine 28 and the scanner 30. In Figure 1 a hard copy page 32 is input through scanner 30 and its digital image appears in the display window of document browser 20.
The scanned images from the input devices such as fax machine 26, photocopier 28 and scanner 30 may be stored as bitmapped images in a variety of commercially available formats. The image data may be compressed, if desired. Alternatively, the image data may be converted to vector graphic data and stored in that form.
In addition to scanned document images, the document database can also store documents that are generated by software applications such as word processors, multimedia authoring applications, graphic illustration applications, computer-aided design applications, spreadsheet applications, on-line and network-based applications (such as those generating documents for the World Wide Web, in HTML or the like). These applications may run on one or more workstations connected to network 14. The document database may be distributed over a number of machines, or over a local or wide area network.

There is no requirement that all devices be connected at all times to the network. Document data may be added to the database in real-time or batched mode, by direct connection to the network or over any suitable telecommunications link.
In a typical office setting the digital output of a suitably equipped photocopier may be connected to the data processing network, along with a suitable number of workstations, fax machines and scanners deployed throughout the workspace. The document database may reside on a file server that may optionally be used for other purposes such as supporting other office automation functions. Hard copies of documents may be printed using any network printer or workstation printer.
For a better understanding of the capabilities of the invention, refer to Figure 2, which shows the browser application 20 in greater detail.
In this regard, the particular configuration and layout of the various windows and user controls represents one of many possible configurations. Other arrangements are possible without departing from the spirit of the invention.
In Figure 2 the image of a selected document is displayed in display window 24. For illustration purposes here, an image of document 32 is displayed. At the upper right-hand segment of the screen 36 there is a series of thumbnail sketches of various document pages that have been located by the search engine for selection by the user. The thumbnail sketch of the currently selected document image is highlighted, as with highlight box 38.
To select a different image for viewing, the user simply selects a different thumbnail sketch with the pointer cursor or annotation pen cursor. In this regard, the cursor 40 may be controlled by moving the mouse or by positioning the pen at a preselected location on the tablet. The thumbnail sketches are tied to a scroll bar 42 that the user can manipulate to scroll through and display different thumbnail sketches in the thumbnail display region 36.
Several user-selectable push button controls are provided in the lower right-hand portion of the display. These include alternately selectable cursor and pen buttons 44 and 46. When the cursor button is selected, as illustrated here, the standard pointer cursor 40 is displayed. When the pen button 46 is selected, the annotation pen cursor is displayed instead of the pointer cursor. The annotation pen cursor (which will be illustrated and described more fully later) identifies the location at which user-drawn annotations will be placed on the digital image of the document.
In addition to these two buttons, the presently preferred embodiment also provides a delete note button 50 for deleting an annotation, an undelete note button 52 for undeleting a deleted annotation, and a hide notes button 54 for hiding all annotations without deleting them. The buttons are modal; their functions change depending on whether an annotation has been selected or not. If a document (but no annotation) is selected, then the delete and undelete operations are performed on the document (the corresponding labels on the buttons are changed to so indicate). If an annotation is selected, then the buttons function as described above to delete 21 ~ 1 78 and undelete the selected annotation. The hide notes button 54 is also modal.
It changes to "show notes" whenever the notes are hidden.
In Figure 2 several separate annotations have been illustrated.
Specifically, a first annotation appears at 60, a second annotation at 62 and a third annotation at 64. Note that the third annotation is a series of nontext symbols or pictures.
In the presently preferred embodiment the browser application displays user-drawn annotations in a different color, such as in red ink, making the annotations readily stand out from the remainder of the displayed document.
Adding annotations to a document is easy. Referring to Figure 3, the user simply activates the pen button 46 to display the pen cursor 48.
Then, using the pen 22 and digitizing tablet 24 (or other suitable drawing tool provided) the user simply positions the pen cursor above the area he or she wishes to annotate and then begins writing or drawing. Any mistakes during creation of the annotation may be corrected using the ink edit slider bar 66.
As will be more fully explained below, annotations are stored as sequential space/time data. Each stroke of the user's pen is recorded somewhat analogous to a digital movie. The ink edit slider bar deletes the pen stroke data, proceeding backward in time from the end of the final stroke towards the beginning of the first stroke. Any strokes deleted in using the slider bar may be undeleted by sliding the slider bar in the opposite 219517~

direction. A permanent deletion takes effect only when a new annotation is begun.
Figure 3 illustrates the operation of the ink edit slider bar.
In Figure 3 at A a nontext user annotation is illustrated in its entirety.
At B the last drawn ink strokes are deleted from the annotation by activating the left-hand slider bar button with pointer cursor 40. Note that the slider bar position indicator 66a has moved to the left as the left-hand slider bar button is actuated. Note that this has erased the "face" from the oval annotation. As further indicated at C, continued activation of the left-hand slider bar button by pointer cursor 40 erases even more of the user-drawn annotation, in reverse sequence to the manner in which it was drawn. Again note that the position indicator 66a has moved still farther to the left. As illustrated at D, the erasure can be reversed by activating the right-hand slider bar button by the pointer cursor 40. In this case, the slider bar indicator 66a moves to the right and a portion of the user-drawn annotation is restored. The slider bar thus operates to fully erase and fully restore the user-drawn annotation, simply by actuation of the respective left-hand and right-hand slider bar buttons.
The ink edit slider bar allows the user to pick up the pen and write more after having deleted some of the ink using the slider.
The ink edit slider bar can be implemented in alternate ways. It may be implemented as a stroke-based procedure, in which case entire pen strokes are deleted and undeleted at once. Alternatively, the ink edit slider -bar may be implemented as a point-based procedure, in which case the delete and undelete operations are performed on a point-by-point or pixel-by-pixel basis. The application would work essentially the same way as far as the user is concerned, although the point-based procedure would allow for a more fine-grained control over annotation editing.
The presently preferred embodiment displays the user-drawn annotations directly on the face of the document. If desired, the user annotation can be displayed as if drawn on an opaque stick-on note, to simulate the appearance of a note adhered to the face of the document. In this case, a rectangular area is defined around the user-drawn annotation and the rectangular area is filled in with a user-selected background color that opaquely covers that portion of the document page behind the rectangular area.
One of the advantages of the preferred embodiment is the ability to record multiple annotations on a single page. The system automatically treats as separate annotations those pen strokes that are (a) at spatial locations separated by more than a predetermined distance; (b) drawn at different times (i.e. at a temporal spacing above a predetermined time limit);
or (c) where there is some user interface activity between two annotations (such as an operation of one of the user interface buttons).
All user-drawn annotations, entered in this fashion, are stored in association with a given page of the document. Using the workstation's printer, or a printer attached to the network, the document page can be printed either with or without the annotations, simply by selecting or deselecting the hide notes button.

21~5178 ~ The true power of the invention is fully realized through the annotation search capability. By pressing the annotation search button 67 a query dialog box 68 is presented as illustrated in Figure 4. To search for a document containing any user-drawn annotation, the user simply draws all, or even part of, the desired annotation in the query dialog box and then engages the search engine by actuating the find button 70. The query dialog box also includes the ink edit slider bar that operates as previously described, and also a dismiss button 72 that is used to cancel a query search request and return to the main view window. Because the system is event-driven, the query dialog box can be made to disappear by simply selecting another window on the display screen.
Actuation of the find button causes the search engine to search the stored annotations for those annotations that represent a possible match with the query. A partial match search procedure is used that ranks annotation data according to how closely or poorly each annotation matches the query. The n-best matches are then displayed, in order of "goodness" in the thumbnail sketches of the main browser screen. In addition, the "best" match is also displayed in the main display window, as illustrated in Figure 4. In the presently preferred embodiment all documents that contain annotations are ranked and displayed in the appropriate order. Thus the n-best matches would represent all matches.
Because a given page may contain multiple annotations, the preferred embodiment highlights the specific annotation that corresponds to the match in question. The presently preferred embodiment highlights the specific annotation by drawing a bounding box 38 around it. Of course, other forms of image highlighting may also be used, such as altering the color or intensity of the annotation, blinking the annotation, and so forth.
By repeatedly actuating the find button 70, the user can cycle through the ranked list, with the associated documents being displayed in the main browser window. To supply the user interface cue of this functionality, the label of the find button 70 changes to "next" upon display of the ranked list corresponding to a particular query.
Thanks to the partial match (word spotting) procedure, the search engine is able to search for substrings within complete annotations. This is illustrated in Figure 4. In Figure 4 a substring match is performed to locate the word "important" within the full string "This is very important!" This is an important feature, for it allows the user to find a relevant annotation, even if he or she cannot remember the precise wording of the complete annotation. Although the partial match procedure is referred to herein as a word spotting procedure, the procedure is not limited to text. The partial match or word spotting procedure works equally well with nontext user-drawn annotations.
As will be more fully explained below, the partial match procedure is a fuzzy search procedure that identifies and ranks possible substring match candidates based on a scoring and ranking distance between the query and the candidate. The procedure produces a score for each candidate, allowing the 2lssl7a candidates to be ranked in order of "goodness." This is illustrated in Figure 8, wherein the query searches for all occurrences of the user-drawn query "important." In Figure 8 the candidate receiving the highest score (in this case a score of 26) appears at the top of the sorted list. The first click of the find button will return the best match, which is ranked highest in the ink search. Repeated use of the find button will continue to find the next best match, working down the sorted list from top to bottom.
Figure 9 shows the word spotting capability of the substring match procedure. In Figure 9 several example queries and corresponding annotations are presented. In each case, the matching procedure is able to identify a matching substring within the full annotation.
Another benefit of the partial match procedure is that line breaks in the user-drawn annotation or query have no impact on the ink search. This is illustrated in Figure 10, where the user-drawn annotation appears as two lines, whereas the query is entered as one line. The line break in writing the annotation is ignored so that the user does not have to remember where the line breaks may have occurred in the original annotation.
The fuzzy search technique of the preferred embodiment uses a vector quantized (VQ) representation of the user-drawn annotations to capture and compare pen strokes of the ink data type. Figure 11 gives an overview of the manner in which pen stroke classification is performed using vector quantization. The ink data type records the motion of the pen tip over the surface of the digitizing tablet as a string of (X,Y) ink points. The individual (X,Y) ink points are sequentially captured, thereby preserving the 21 951 7~
-temporal or time-based component of the data. Thus the ink data type may be considered as comprising (X,Y,T) vectors.
As illustrated in Figure 11, the incoming ink data 200 is broken into strokes as at 202. Segmenting the ink data into strokes allows each stroke to be analyzed separately. By way of illustration, Figure 11 shows that the plus sign (+) in the incoming data 200 was drawn by the user first forming a horizontal line and then forming a vertical line. This is illustrated at Z02 by reading the segmented data at 202 from left to right.
After stroke segmentation the individual strokes are then analyzed to extract feature vectors. This is shown diagrammatically at 204. In Figure 11, the extracted feature vectors are shown graphically to simplify the presentation. In the actual embodiment, the extracted feature vectors are represented as numerical data that is stored in the computer. As indicated at 206, each extracted feature vector is classified according to a predetermined code book 210. The presently preferred embodiment stores 64 clusters of stroke types, each cluster being represented by its centroid or average stroke of that type. As in the case of the extracted feature vectors (block 204) the feature vector clusters are stored as numerical computer data.
In Figure 11 the data comprising code book 210 are shown graphically (instead of numerically) to simplify the presentation. In Figure 11 note that the horizontal line segment of block 206 most closely matches the centroid 212 of the Type 2 stroke cluster 214. Thus in the output string (block 216) the VQ
code 2 is used to represent the horizontal line in block 206. In block 216 2~9~178 the leftmost numeral 2 corresponds to the leftmost horizontal line stroke.
The remaining codes represent the remaining ink strokes comprising the original incoming ink data.
Through the above-described procedure the incoming ink data is converted, pen stroke by pen stroke, into a feature vector that is then stored in the computer database as the user-drawn annotation. This is depicted at 218.
To further illustrate, a software block diagram of the presently preferred embodiment is shown in Figure 5. The annotation system operates on digitized pen stroke data that is ultimately represented as an "ink" data type. As will be illustrated, it is not necessary to convert the ink data type into an ASCII character data type in order to perform the search and retrieval procedures. Indeed, in the case of graphical (nontext) annotations, conversion to ASCII would have no meaning.
Illustrated in Figure 5, the user-drawn query 100 is captured as a string of (X,Y) ink points, corresponding to the motion of the pen tip over the surface of the digitizing tablet or pad as the user draws query 100. The presently preferred embodiment digitizes this information by sampling the output of the digitizing pad at a predetermined sampling rate. Although a fixed sampling rate is presently preferred, the invention can be implemented using a variable sampling rate, as well. By virtue of the digitized capture of the X,Y position data, both spatial and temporal components of the user-drawn pen strokes are captured.

2 1 95 1 7~

~ In the presently preferred embodiment, employing a fixed sampling rate, each X,Y data point is associated with a different sampling time.
Because the sampling rate is fixed, it is not necessary to store the sampling time in order to store the temporal data associated with the pen stroke.
Simply recording the X,Y position data as a sequence automatically stores the temporal data, as each point in the sequence is known to occur at the next succeeding sampling time.
In the alternative, if a variable sampling rate system is implemented, (X,Y,T) data is captured and stored. These data are the (X,Y) ink points and the corresponding time T at which each ink point is captured.
The raw ink point data is stored in data store 102. Next, a segmentation process 104 is performed on the stored ink point data 10Z. The presently preferred segmentation process searches the ink point data 102 for Y-minima. That is, the segmentation process 104 detects those local points at which the Y value coordinate is at a local minimum. In hand-drawing the letter "Y" as a single continuous stroke, the lowermost point of the letter "V" would represent a Y-minima value.
Segmentation is performed to break the raw ink point data into more manageable subsets. These segment subsets may be designated using suitable pointers to indicate the memory locations at which the Y-minima occur. In this case, these segmentation pointers may be stored at 106 to be associated with the ink point data 102 previously captured. In the alternative, if desired, the segmented data may be separately stored in one or more memory buffers instead of using pointers.
Once the raw data has been segmented the individual segments or pen strokes are operated on by a set of extraction functions 108. The presently preferred embodiment operates on the pen stroke (segment) data using 13 different extraction functions. These extraction functions each extract a different feature of the pen stroke data that are then used to construct a feature vector. Table I lists the presently preferred features that are extracted by the extraction functions 108. For further background information on these extraction functions, see Rubine, Dean, "Specifying Gestures by Example," Computer Graphics, Vol. 25, No. 4, July 1991. The feature vectors of a given stroke are diagrammatically represented in Figure 5 at 110.

2 1 9~ 1 78 ~ TABLE I

f = X2 - xO
\l(X - X ) 2 + (y _ y ) 2 f _ Y2 - Yo ~(X2 - Xo ) + (Y2 - Yo ) f3 = \I(xmax Xmin ) + (Ymax Ymin ) f 4 = arctan( X --X j f5 = ~(Xp I - Xo)2 + (YP-I - Yo) f X p_l --Xo fs f = YP_I--Yo f5 Let ~xp = xp+~ -xp and ~Yp = YP+I -Yp and ~tp = tp+l -tp f8 = ~ Xp + ~y2 fg = 2~f~P

fio = ~PI

fil = 2~J2p P=l f P-2 ~xp + Ayp fl3 = tp_l--to Where P represents the total number of points.

-~ The extracted feature vectors represented at 110 are then coded or quantized by comparison with a predetermined set of clusters of stroke data types. The feature vector data 110 i s quantized by vector quantization process 112 to assign each cluster to the closest predetermined stroke type.
In this regard, the presently preferred embodiment defines 64 different stroke types that are each represented by a different name or number. Although the presently preferred system uses 64 different stroke types, the principles of the invention can be employed with a greater or fewer number of stroke types.
The predetermined stroke types are arrived at during a training procedure 113. The training procedure may be used to predetermine a vector quantization (VQ) code book 114 that is then used for multiple users.
Alternatively, the training procedure can be used prior to use by an individual user. Both applications work well. In either case, the system is still user-dependent because there can be a great deal of variation in the way two different people draw the same annotation. Thus the preferred embodiment is best suited to searching one's own annotations.
If the document database is shared among multiple users, it is possible for each user to have his or her own personal set of annotations that can be searched and that are nevertheless "invisible" to everyone else.
Alternatively, the annotations may be shared, too. As noted above, shared annotations are more difficult to implement due to the potential variation in the way different people draw the same annotation.

2 t 95~ 78 -~ Training involves processing a small portion of training data that the user inputs by hand using the digitizing tablet and pen. The training data are processed by segmentation and feature extraction, as discussed above.
The resulting feature vectors from the training data are then processed using conventional clustering techniques that identify the 64 most disparate clusters to represent the 64 stroke types for that training sequence.
Numerical values or suitable other naming conventions are used to name each of the identified stroke types in the training set. These data are then stored as a code book of the user-dependent stroke types 114. These stored training data values are used in performing the vector quantization process 112.
Essentially, the stroke data for a given user-drawn annotation may be considered as a string of symbols. As originally input in the form of raw (X,Y,T) data, the string of symbols correspond to actual spatial and temporal components of the pen stroke across the digitizing tablet. Through the series of processing steps described above, this string of symbols is converted into a string of symbols of the stroke data type, i.e. a string of vector quantized symbols stored at 115.
It will be appreciated that in most cases the user will not draw the same annotation in precisely the same way each and every time. That is, the (X,Y,T) coordinates and temporal properties of a given annotation may vary somewhat, each time the user draws that annotation. The presently preferred system accommodates this variation first by the manner in which the vector 21qS I 78 quantization is performed. Specifically, the vector quantization process 112 assigns each input stroke to the predetermined vector from the user-dependent stroke types 114 that represents the closest match.
After each of the strokes representing the query has been processed in this fashion, a comparison is made between those strokes and the user-drawn annotations that have been stored in association with the documents in the database 120. Thus, for example, the query "important" may be compared against the stored annotation "this is very important!" An edit distance analysis is performed to make this comparison.
Shown as edit distance analysis process 118, the query stroke type string is compared with each of the stored annotation stroke type strings 121 of the database 120. The edit distance analysis compares each stroke type value in the query string with each stroke type value in each of the annotation strings. A edit distance computation is performed by this comparison, yielding the "cost" of transforming (or editing) one string into the other. The individual string/string comparisons are then ranked according to cost, with the least cost resultants presented first. In this way, a sorted list comprising all or the n-best matches is displayed in the thumbnail sketches of the main browser screen.
Figure 6 shows the basic edit distance technique. In this case, the stored annotation "compress" is compared with the query string "compass."
It should be understood that Figure 6 depicts the comparison of two strings as a comparison of individual letters in two differently spelled words. This depiction is intended primarily to aid in understanding the edit distance computation technique and not necessarily as a depiction of what two stroke type strings might actually look like. In this regard, each of the 64 different stroke types may be arbitrarily assigned different numerical labels.
Thus the edit distance computation would compare the respective numeric labels of the stored annotation and the input query directly with each other. There is no need to convert the individual strings into ASCII characters and Figure 6 is not intended to imply that such conversion is necessary.
Referring to Figure 6, each time the annotation string stroke value matches the query string stroke value a cost of zero is assigned. Thus in Figure 6, a zero cost is entered for the comparison of the first four string values "comp." To accommodate the possibility that a string/string comparison may involve insertion, deletion or substitution of values, a cost is assigned each time an insertion, deletion or substitution must be made during the comparison sequence. In the example of Figure 6, the query string "compass" requires insertion of an additional value "r" after the value "p."
A cost of one is assigned (as indicated at the entry designated 122).
Continuing with the comparison, a substitution occurs between the value "e"
of the stored annotation string and the value "a" of the query string. This results in an additional cost assignment of one being added to the previous cost assignment, resulting in a total cost of two, represented in Figure 6 at 124. Aside from these insertion and substitution operations, the remainder of the comparisons match, value for value. Thus, the final "cost" in comparing the annotation string with the query string is two, represented in Figure 6 at 126.
In the preceding discussion, a first minimum cost path was described in which "compass" is edited into "compress" by inserting an "r" and substituting an "e" for an "a." An alternative edit would be to substitute an "r" for an "a" and inserting an "e." Both of these paths have the same cost, namely two.
Figure 7 gives another example of the edit distance computation technique. As before, strings of alphabetic characters are compared for demonstration purposes. As previously noted, this is done for convenience, to simplify the illustration, and should not be interpreted as implying that the strings must be first converted to alphanumeric text before the comparisons are made. Rather, the procedure illustrated in Figures 6 and 7 are performed on the respective stroke data (vector quantized symbols) of the respective stored annotation and input query strings.
Figure 7 specifically illustrates the technique that may be used to perform a partial match (word spotting). In Figure 7 the stored annotation "This is compression," is compared with the query string "compass." Note how the matched region 130 is extracted from the full string of the stored annotation by scanning the last row of the table to find the indices that represent the lowest value. Note that the first (initializing) row in Figure 7 is all Os - this allows the partial match to start anywhere along the database string.

2 1 95 1 7~

~ The presently preferred edit distance procedure is enhanced over the conventional procedures described in the literature. Specifically, we have determined that in addition to the three basic editing operations (delete a character, insert a character, and substitute one character for another), it is useful to add two new operations when comparing pen stroke sequences.
These new operations are "split" (substitute two characters for one character) and "merge" (substitute one character for two characters). These additional operations allow for errors made in stroke segmentation and generally leads to more accurate results.
The use of our enhanced edit distance procedure is illustrated in Figure 7. In Figure 7 the split operation is used to substitute the letters "re" in "compress" for the letter "a" in "compass." Note that the backtracking arrow in Figure 7 spans one row but two columns, thereby signifying the multicharacter (merge) substitution. Hence the edit distance is one, not two, in this case. By way of comparison, Figure 6 illustrates the basic edit distance algorithm without utilizing the two new multicharacter operations. Thus the cost (as depicted in Figure 6) of editing "compass" into "compress" is two.
The above-described procedure works well in most user-drawn annotation applications. The combined use of vector quantizing and edit distance computation yield a system that is remarkably robust in its ability to find matching strings and substrings, even if they are not drawn precisely the same way by the user. Although the presently preferred embodiment has been illustrated here, a number of variations are possible without departing from the spirit of the invention. For example, if a faster match is desired, the system may perform an initial "first pass" match by simply finding all strokes that have a similar number of data points. This may be done by storing the number of data points as part of the feature data and then simply selecting or excluding those strokes that are not within a predetermined data point count. This type of first pass search can be performed quite quickly, as simple numeric matching algorithms are all that are required. The first pass technique based on data point count would not, however, allow matching substrings to be extracted as the edit distance computation permits. Where higher matching accuracy is desired a more computationally costly matching technique such as a Hidden Markov Model technique may be used as a final pass on the n-best hypotheses determined by the edit distance computation. Adding a highly accurate, but computationally costly processing stage to the final output may be used in systems where it is necessary to discriminate between a large number of highly similar strings.

Claims (14)

1. A document search and retrieval system comprising:
a memory having a first data structure for storing document data and a second data structure for storing annotation data;
a user interface having drawing tool for user input of stroke data corresponding to a user-drawn symbol, said stroke data having spatial and temporal components;
said user interface communicating with said second data structure to store said spatial and temporal components of said stroke data in association with a user-selected portion of said document data;
a search engine communicating with said user interface for receiving a user-drawn search symbol comprising said stroke data;
said search engine communicating with said second data structure for matching patterns in the spatial and temporal components of a user-drawn search symbol with patterns in the spatial and temporal components of stroke data stored in said second data structure to locate a match hypothesis;
said search engine accessing said first data structure to select a portion of said document data corresponding to the match hypothesis and thereby retrieve a portion of said document data that has an associated user-drawn symbol that substantially corresponds to said search symbol.
2. The system of Claim 1 further comprising a document viewer communicating with said memory and with said user interface for displaying an image of a selected portion of said document data and for displaying user-drawn symbols associated with said selected portion.
3. The system of Claim 1 wherein at least a portion of said user-drawn symbol comprises a nontext symbol.
4. The system of Claim 1 wherein at least a portion of said search symbol comprises a nontext symbol.
5. The system of Claim 1 further comprising stored rules set associated with said user interface and with said memory for storing a plurality of separate stroke data corresponding to separate user-drawn symbols in association with the same user-selected portion of said document data.
6. The system of Claim 5 wherein said rules set distinguishes separate stroke data by detecting time elapsed between a first stroke and a second stroke.
7. The system of Claim 5 wherein said rules set distinguishes separate stroke data by detecting spatial separation between a first stroke and a second stroke.
8. The system of Claim 5 wherein said rules set distinguishes separate stroke data by detecting performance of a user interface control operation between a first stroke and a second stroke.
9. The system of Claim 1 wherein said spatial component comprises a datum indicative of the relative position of said drawing tool.
10. The system of Claim 1 wherein said temporal component comprises a datum indicative of the relative time at which said drawing tool is at a given position.
11. The system of Claim 1 wherein said drawing tool comprises a pen and digitizing tablet.
12. The system of Claim 1 further comprising image scanning means for storing document data in said first data structure.
13. The system of Claim 12 wherein said image scanning means comprises a photocopy machine.
14. The system of Claim 12 wherein said image scanning means comprises a photocopy machine and wherein said memory comprises a component of a computer network system coupled to said photocopy machine.
CA002195178A 1996-02-26 1997-01-15 Document search and retrieval system with partial match searching of user-drawn annotations Abandoned CA2195178A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US08/606,575 US5832474A (en) 1996-02-26 1996-02-26 Document search and retrieval system with partial match searching of user-drawn annotations
US08/606,575 1996-02-26

Publications (1)

Publication Number Publication Date
CA2195178A1 true CA2195178A1 (en) 1997-08-27

Family

ID=24428527

Family Applications (1)

Application Number Title Priority Date Filing Date
CA002195178A Abandoned CA2195178A1 (en) 1996-02-26 1997-01-15 Document search and retrieval system with partial match searching of user-drawn annotations

Country Status (5)

Country Link
US (1) US5832474A (en)
EP (1) EP0791883B1 (en)
JP (1) JPH1055371A (en)
CA (1) CA2195178A1 (en)
DE (1) DE69731418T2 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014075174A1 (en) * 2012-11-19 2014-05-22 Imds America Inc. Method and system for the spotting of arbitrary words in handwritten documents

Families Citing this family (297)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AUPQ131399A0 (en) * 1999-06-30 1999-07-22 Silverbrook Research Pty Ltd A method and apparatus (NPAGE02)
US8352400B2 (en) 1991-12-23 2013-01-08 Hoffberg Steven M Adaptive pattern recognition based controller apparatus and method and human-factored interface therefore
US5625711A (en) 1994-08-31 1997-04-29 Adobe Systems Incorporated Method and apparatus for producing a hybrid data structure for displaying a raster image
US5729637A (en) 1994-08-31 1998-03-17 Adobe Systems, Inc. Method and apparatus for producing a hybrid data structure for displaying a raster image
JP3535624B2 (en) * 1995-09-21 2004-06-07 キヤノン株式会社 Search device and method
US6295524B1 (en) * 1996-10-29 2001-09-25 Nec Research Institute, Inc. Learning edit distance costs
US6704118B1 (en) 1996-11-21 2004-03-09 Ricoh Company, Ltd. Method and system for automatically and transparently archiving documents and document meta data
US6199073B1 (en) * 1997-04-21 2001-03-06 Ricoh Company, Ltd. Automatic archiving of documents during their transfer between a peripheral device and a processing device
US7170629B2 (en) * 1998-11-13 2007-01-30 Ricoh Company, Ltd. Automatic and transparent document archiving
US5978477A (en) * 1996-11-21 1999-11-02 Ricoh Company Limited Automatic and transparent document archiving
US7602518B2 (en) * 1996-11-21 2009-10-13 Ricoh Company, Ltd. Automatic and transparent document archiving
US6366956B1 (en) * 1997-01-29 2002-04-02 Microsoft Corporation Relevance access of Internet information services
JP3195752B2 (en) * 1997-02-28 2001-08-06 シャープ株式会社 Search device
US6332148B1 (en) * 1997-03-31 2001-12-18 Adobe Systems Incorporated Appearance and positioning annotation text string and base text string specifying a rule that relates the formatting annotation, base text characters
JPH1186014A (en) * 1997-09-08 1999-03-30 Fujitsu Ltd Method and device for displaying document image
US6279014B1 (en) 1997-09-15 2001-08-21 Xerox Corporation Method and system for organizing documents based upon annotations in context
US6613100B2 (en) * 1997-11-26 2003-09-02 Intel Corporation Method and apparatus for displaying miniaturized graphical representations of documents for alternative viewing selection
US6138129A (en) * 1997-12-16 2000-10-24 World One Telecom, Ltd. Method and apparatus for providing automated searching and linking of electronic documents
US6269362B1 (en) * 1997-12-19 2001-07-31 Alta Vista Company System and method for monitoring web pages by comparing generated abstracts
US7124093B1 (en) 1997-12-22 2006-10-17 Ricoh Company, Ltd. Method, system and computer code for content based web advertising
US6804659B1 (en) 2000-01-14 2004-10-12 Ricoh Company Ltd. Content based web advertising
JP4183311B2 (en) 1997-12-22 2008-11-19 株式会社リコー Document annotation method, annotation device, and recording medium
US7596755B2 (en) 1997-12-22 2009-09-29 Ricoh Company, Ltd. Multimedia visualization and integration environment
US7954056B2 (en) 1997-12-22 2011-05-31 Ricoh Company, Ltd. Television-based visualization and navigation interface
US7263659B2 (en) 1998-09-09 2007-08-28 Ricoh Company, Ltd. Paper-based interface for multimedia information
US7257589B1 (en) 1997-12-22 2007-08-14 Ricoh Company, Ltd. Techniques for targeting information to users
JP3692764B2 (en) * 1998-02-25 2005-09-07 株式会社日立製作所 Structured document registration method, search method, and portable medium used therefor
US6799298B2 (en) * 1998-03-11 2004-09-28 Overture Services, Inc. Technique for locating an item of interest within a stored representation of data
US6173287B1 (en) * 1998-03-11 2001-01-09 Digital Equipment Corporation Technique for ranking multimedia annotations of interest
US6598045B2 (en) * 1998-04-07 2003-07-22 Intel Corporation System and method for piecemeal relevance evaluation
US6370551B1 (en) * 1998-04-14 2002-04-09 Fuji Xerox Co., Ltd. Method and apparatus for displaying references to a user's document browsing history within the context of a new document
US6272484B1 (en) * 1998-05-27 2001-08-07 Scansoft, Inc. Electronic document manager
US6766494B1 (en) * 1998-06-15 2004-07-20 Fuji Xerox Co., Ltd. Method and system for creating ad-hoc links from free-form ink
US6369811B1 (en) 1998-09-09 2002-04-09 Ricoh Company Limited Automatic adaptive document help for paper documents
US7263671B2 (en) * 1998-09-09 2007-08-28 Ricoh Company, Ltd. Techniques for annotating multimedia information
US7215436B2 (en) 1998-09-09 2007-05-08 Ricoh Company, Ltd. Device for generating a multimedia paper document
US6582475B2 (en) * 1998-09-09 2003-06-24 Ricoh Company Limited Automatic adaptive document printing help system
US7266782B2 (en) * 1998-09-09 2007-09-04 Ricoh Company, Ltd. Techniques for generating a coversheet for a paper-based interface for multimedia information
JP2002528819A (en) 1998-10-28 2002-09-03 バーティカルワン コーポレイション Automatic aggregation device and method, device and method for delivering electronic personal information or data, and transaction involving electronic personal information or data
US6871220B1 (en) 1998-10-28 2005-03-22 Yodlee, Inc. System and method for distributed storage and retrieval of personal information
US6845370B2 (en) 1998-11-12 2005-01-18 Accenture Llp Advanced information gathering for targeted activities
US6684368B1 (en) 1998-11-13 2004-01-27 Ricoh Company, Ltd. Method for specifying delivery information for electronic documents
US6725425B1 (en) * 1998-12-08 2004-04-20 Yodlee.Com Method and apparatus for retrieving information from semi-structured, web-based data sources
US7672879B1 (en) 1998-12-08 2010-03-02 Yodlee.Com, Inc. Interactive activity interface for managing personal data and performing transactions over a data packet network
US8069407B1 (en) 1998-12-08 2011-11-29 Yodlee.Com, Inc. Method and apparatus for detecting changes in websites and reporting results to web developers for navigation template repair purposes
US7085997B1 (en) 1998-12-08 2006-08-01 Yodlee.Com Network-based bookmark management and web-summary system
US6687876B1 (en) * 1998-12-30 2004-02-03 Fuji Xerox Co., Ltd. Method and system for maintaining freeform ink annotations on changing views
US6941321B2 (en) * 1999-01-26 2005-09-06 Xerox Corporation System and method for identifying similarities among objects in a collection
US6922699B2 (en) * 1999-01-26 2005-07-26 Xerox Corporation System and method for quantitatively representing data objects in vector space
US7904187B2 (en) 1999-02-01 2011-03-08 Hoffberg Steven M Internet appliance system and method
US6687878B1 (en) * 1999-03-15 2004-02-03 Real Time Image Ltd. Synchronizing/updating local client notes with annotations previously made by other clients in a notes database
US6428155B1 (en) * 1999-05-25 2002-08-06 Silverbrook Research Pty Ltd Printer cartridge including machine readable ink
US7760969B2 (en) * 1999-05-25 2010-07-20 Silverbrook Research Pty Ltd Method of providing information via context searching from a printed substrate
US7752535B2 (en) 1999-06-01 2010-07-06 Yodlec.com, Inc. Categorization of summarized information
US6647534B1 (en) 1999-06-30 2003-11-11 Ricoh Company Limited Method and system for organizing document information in a non-directed arrangement of documents
US7228492B1 (en) * 1999-07-06 2007-06-05 Ricoh Company, Ltd. 2D graph displaying document locations of user-specified concept of interest
JP2001052116A (en) * 1999-08-06 2001-02-23 Toshiba Corp Device and method for matching pattern stream, device and method for matching character string
US6519050B1 (en) 1999-08-18 2003-02-11 Rtimage Ltd. Client/server based color density measurement system
GB2354099B (en) * 1999-09-09 2003-09-10 Sony Uk Ltd Image identification apparatus and method of identifying images
US6519603B1 (en) * 1999-10-28 2003-02-11 International Business Machine Corporation Method and system for organizing an annotation structure and for querying data and annotations
US7337389B1 (en) 1999-12-07 2008-02-26 Microsoft Corporation System and method for annotating an electronic document independently of its content
JP2001209659A (en) * 1999-12-15 2001-08-03 Xerox Corp System and method for annotating object in the case that annotation device is different from viewing device
US6766069B1 (en) * 1999-12-21 2004-07-20 Xerox Corporation Text selection from images of documents using auto-completion
US6859909B1 (en) * 2000-03-07 2005-02-22 Microsoft Corporation System and method for annotating web-based documents
US6681044B1 (en) 2000-03-29 2004-01-20 Matsushita Electric Industrial Co., Ltd. Retrieval of cursive Chinese handwritten annotations based on radical model
KR20000037200A (en) * 2000-04-11 2000-07-05 김병철 Virtual Layer based Internet World Wide Web document(HTML) explanatory notes and save method
US20050177574A1 (en) * 2000-05-08 2005-08-11 James Riley Electronic course generation systems and methods
US6625335B1 (en) 2000-05-11 2003-09-23 Matsushita Electric Industrial Co., Ltd. Method and apparatus for assigning keywords to documents
US7039864B1 (en) * 2000-05-15 2006-05-02 Ricoh Co., Ltd. Method and apparatuses for management of unconsciously captured documents
US20010053252A1 (en) * 2000-06-13 2001-12-20 Stuart Creque Method of knowledge management and information retrieval utilizing natural characteristics of published documents as an index method to a digital content store
US6671684B1 (en) * 2000-09-01 2003-12-30 Ricoh Co., Ltd. Method and apparatus for simultaneous highlighting of a physical version of a document and an electronic version of a document
FR2814829B1 (en) * 2000-09-29 2003-08-15 Vivendi Net METHOD AND SYSTEM FOR OPTIMIZING CONSULTATIONS OF DATA SETS BY A PLURALITY OF CLIENTS
AU2002225822A1 (en) * 2000-10-31 2002-05-15 Contextweb Internet contextual communication system
US7069545B2 (en) * 2000-12-29 2006-06-27 Intel Corporation Quantization and compression for computation reuse
US7056161B2 (en) * 2001-02-20 2006-06-06 Newfrey Llc Grounding stud
US7392287B2 (en) 2001-03-27 2008-06-24 Hemisphere Ii Investment Lp Method and apparatus for sharing information using a handheld device
JP2002324037A (en) * 2001-04-24 2002-11-08 Fujitsu Ltd Coordinated display program
US20030004991A1 (en) * 2001-06-29 2003-01-02 Keskar Dhananjay V. Correlating handwritten annotations to a document
KR20030003787A (en) * 2001-07-02 2003-01-14 조미경 Personal information searching system using the partial matching in the electronic ink domain
US7885987B1 (en) * 2001-08-28 2011-02-08 Lee Eugene M Computer-implemented method and system for managing attributes of intellectual property documents, optionally including organization thereof
AUPR824301A0 (en) * 2001-10-15 2001-11-08 Silverbrook Research Pty. Ltd. Methods and systems (npw001)
US8635531B2 (en) 2002-02-21 2014-01-21 Ricoh Company, Ltd. Techniques for displaying information stored in multiple multimedia documents
US7788080B2 (en) 2001-11-19 2010-08-31 Ricoh Company, Ltd. Paper interface for simulation environments
US8539344B2 (en) 2001-11-19 2013-09-17 Ricoh Company, Ltd. Paper-based interface for multimedia information stored by multiple multimedia documents
US7703044B2 (en) 2001-11-19 2010-04-20 Ricoh Company, Ltd. Techniques for generating a static representation for time-based media information
US7149957B2 (en) 2001-11-19 2006-12-12 Ricoh Company, Ltd. Techniques for retrieving multimedia information using a paper-based interface
US7747655B2 (en) 2001-11-19 2010-06-29 Ricoh Co. Ltd. Printable representations for time-based media
US7743347B2 (en) 2001-11-19 2010-06-22 Ricoh Company, Ltd. Paper-based interface for specifying ranges
US7495795B2 (en) 2002-02-21 2009-02-24 Ricoh Company, Ltd. Interface for printing multimedia information
US7861169B2 (en) 2001-11-19 2010-12-28 Ricoh Co. Ltd. Multimedia print driver dialog interfaces
US7573598B2 (en) * 2002-01-16 2009-08-11 Infoprint Solutions Company, Llc Method and apparatus for selectively copying documents with handwritten notations
AUPS020302A0 (en) * 2002-01-31 2002-02-21 Silverbrook Research Pty. Ltd. Methods and systems (npw007)
CA2375355A1 (en) * 2002-03-11 2003-09-11 Neo Systems Inc. Character recognition system and method
US7120872B2 (en) * 2002-03-25 2006-10-10 Microsoft Corporation Organizing, editing, and rendering digital ink
US8069175B2 (en) 2002-04-10 2011-11-29 Google Inc. Delegating authority to evaluate content
US7844610B2 (en) * 2003-12-12 2010-11-30 Google Inc. Delegated authority evaluation system
US7453472B2 (en) * 2002-05-31 2008-11-18 University Of Utah Research Foundation System and method for visual annotation and knowledge representation
US7137077B2 (en) * 2002-07-30 2006-11-14 Microsoft Corporation Freeform encounter selection tool
CN100437549C (en) * 2002-09-04 2008-11-26 珠海市零壹网络标准数据有限责任公司 Computer adaption system and method for multivariated information of supply and demand
US7428711B2 (en) * 2002-10-31 2008-09-23 Microsoft Corporation Glow highlighting as an ink attribute
US7092567B2 (en) * 2002-11-04 2006-08-15 Matsushita Electric Industrial Co., Ltd. Post-processing system and method for correcting machine recognized text
US7634729B2 (en) * 2002-11-10 2009-12-15 Microsoft Corporation Handwritten file names
US7284200B2 (en) * 2002-11-10 2007-10-16 Microsoft Corporation Organization of handwritten notes using handwritten titles
US7107520B2 (en) * 2002-11-18 2006-09-12 Hewlett-Packard Development Company, L.P. Automated propagation of document metadata
US7765206B2 (en) * 2002-12-13 2010-07-27 Metaweb Technologies, Inc. Meta-Web
US7310769B1 (en) 2003-03-12 2007-12-18 Adobe Systems Incorporated Text encoding using dummy font
US7552381B2 (en) * 2003-03-31 2009-06-23 Ricoh Co., Ltd. Check boxes for identifying and processing stored documents
US7703002B2 (en) 2003-03-31 2010-04-20 Ricoh Company, Ltd. Method and apparatus for composing multimedia documents
US7509569B2 (en) 2003-03-31 2009-03-24 Ricoh Co., Ltd. Action stickers for nested collections
US7739583B2 (en) 2003-03-31 2010-06-15 Ricoh Company, Ltd. Multimedia document sharing method and apparatus
US7757162B2 (en) 2003-03-31 2010-07-13 Ricoh Co. Ltd. Document collection manipulation
US20070050696A1 (en) * 2003-03-31 2007-03-01 Piersol Kurt W Physical key for accessing a securely stored digital document
US7536638B2 (en) 2003-03-31 2009-05-19 Ricoh Co., Ltd. Action stickers for identifying and processing stored documents
US20040196306A1 (en) * 2003-04-04 2004-10-07 Microsoft Corporation Method and system for flagging digital ink note content
US20040205547A1 (en) * 2003-04-12 2004-10-14 Feldt Kenneth Charles Annotation process for message enabled digital content
US20040243672A1 (en) * 2003-05-27 2004-12-02 Outi Markki System and method for user interaction in a peer-to-peer environment
US20040243665A1 (en) * 2003-05-27 2004-12-02 Outi Markki System and method for services provision in a peer-to-peer environment
US7218783B2 (en) * 2003-06-13 2007-05-15 Microsoft Corporation Digital ink annotation process and system for recognizing, anchoring and reflowing digital ink annotations
US7519901B2 (en) * 2003-06-16 2009-04-14 Fuji Xerox Co., Ltd. Methods and systems for selecting objects by grouping annotations on the objects
US8321470B2 (en) * 2003-06-20 2012-11-27 International Business Machines Corporation Heterogeneous multi-level extendable indexing for general purpose annotation systems
US9026901B2 (en) * 2003-06-20 2015-05-05 International Business Machines Corporation Viewing annotations across multiple applications
US7275159B2 (en) 2003-08-11 2007-09-25 Ricoh Company, Ltd. Multimedia output device having embedded encryption functionality
EP1665086A4 (en) * 2003-08-15 2009-09-02 Silverbrook Res Pty Ltd Improving accuracy in searching digital ink
US7418442B1 (en) * 2003-09-30 2008-08-26 Microsoft Corporation Ink alternates and plain text search
US7870152B2 (en) * 2003-10-22 2011-01-11 International Business Machines Corporation Attaching and displaying annotations to changing data views
US7900133B2 (en) 2003-12-09 2011-03-01 International Business Machines Corporation Annotation structure type determination
US7707039B2 (en) 2004-02-15 2010-04-27 Exbiblio B.V. Automatic modification of web pages
US8442331B2 (en) 2004-02-15 2013-05-14 Google Inc. Capturing text from rendered documents using supplemental information
KR100587540B1 (en) * 2004-02-14 2006-06-08 삼성전자주식회사 Apparatus and method for searching for digital ink query
US10635723B2 (en) 2004-02-15 2020-04-28 Google Llc Search engines and systems with handheld document data capture devices
US7812860B2 (en) 2004-04-01 2010-10-12 Exbiblio B.V. Handheld device for capturing text from both a document printed on paper and a document displayed on a dynamic display device
US20050210038A1 (en) * 2004-03-18 2005-09-22 International Business Machines Corporation Method for providing workflow functionality and tracking in an annotation subsystem
US7779355B1 (en) 2004-03-30 2010-08-17 Ricoh Company, Ltd. Techniques for using paper documents as media templates
US7894670B2 (en) 2004-04-01 2011-02-22 Exbiblio B.V. Triggering actions in response to optically or acoustically capturing keywords from a rendered document
US20060098900A1 (en) 2004-09-27 2006-05-11 King Martin T Secure data gathering from rendered documents
US7990556B2 (en) 2004-12-03 2011-08-02 Google Inc. Association of a portable scanner with input/output and storage devices
US9143638B2 (en) 2004-04-01 2015-09-22 Google Inc. Data capture from rendered documents using handheld device
US8081849B2 (en) 2004-12-03 2011-12-20 Google Inc. Portable scanning and memory device
US9008447B2 (en) 2004-04-01 2015-04-14 Google Inc. Method and system for character recognition
US20060081714A1 (en) 2004-08-23 2006-04-20 King Martin T Portable scanning device
US8146156B2 (en) 2004-04-01 2012-03-27 Google Inc. Archive of text captures from rendered documents
US9116890B2 (en) 2004-04-01 2015-08-25 Google Inc. Triggering actions in response to optically or acoustically capturing keywords from a rendered document
US8713418B2 (en) 2004-04-12 2014-04-29 Google Inc. Adding value to a rendered document
US8489624B2 (en) 2004-05-17 2013-07-16 Google, Inc. Processing techniques for text capture from a rendered document
US8620083B2 (en) 2004-12-03 2013-12-31 Google Inc. Method and system for character recognition
US8874504B2 (en) 2004-12-03 2014-10-28 Google Inc. Processing techniques for visual capture data from a rendered document
JP2005346495A (en) * 2004-06-03 2005-12-15 Oki Electric Ind Co Ltd Information processing system, information processing method, and information processing program
US8316088B2 (en) * 2004-07-06 2012-11-20 Nokia Corporation Peer-to-peer engine for object sharing in communication devices
JP2008506188A (en) * 2004-07-09 2008-02-28 ジェスチャーラド インコーポレイテッド Gesture-based reporting method and system
US8335694B2 (en) * 2004-07-09 2012-12-18 Bruce Reiner Gesture-based communication and reporting system
US8346620B2 (en) 2004-07-19 2013-01-01 Google Inc. Automatic modification of web pages
US7729538B2 (en) * 2004-08-26 2010-06-01 Microsoft Corporation Spatial recognition and grouping of text and graphics
US7574048B2 (en) * 2004-09-03 2009-08-11 Microsoft Corporation Freeform digital ink annotation recognition
US20070118794A1 (en) * 2004-09-08 2007-05-24 Josef Hollander Shared annotation system and method
US8600989B2 (en) * 2004-10-01 2013-12-03 Ricoh Co., Ltd. Method and system for image matching in a mixed media environment
US7917554B2 (en) 2005-08-23 2011-03-29 Ricoh Co. Ltd. Visibly-perceptible hot spots in documents
US9405751B2 (en) 2005-08-23 2016-08-02 Ricoh Co., Ltd. Database for mixed media document system
US9384619B2 (en) 2006-07-31 2016-07-05 Ricoh Co., Ltd. Searching media content for objects specified using identifiers
US8825682B2 (en) 2006-07-31 2014-09-02 Ricoh Co., Ltd. Architecture for mixed media reality retrieval of locations and registration of images
US8156115B1 (en) 2007-07-11 2012-04-10 Ricoh Co. Ltd. Document-based networking with mixed media reality
US8335789B2 (en) 2004-10-01 2012-12-18 Ricoh Co., Ltd. Method and system for document fingerprint matching in a mixed media environment
US8510283B2 (en) 2006-07-31 2013-08-13 Ricoh Co., Ltd. Automatic adaption of an image recognition system to image capture devices
US7702673B2 (en) * 2004-10-01 2010-04-20 Ricoh Co., Ltd. System and methods for creation and use of a mixed media environment
US8176054B2 (en) * 2007-07-12 2012-05-08 Ricoh Co. Ltd Retrieving electronic documents by converting them to synthetic text
US8521737B2 (en) * 2004-10-01 2013-08-27 Ricoh Co., Ltd. Method and system for multi-tier image matching in a mixed media environment
US7991778B2 (en) 2005-08-23 2011-08-02 Ricoh Co., Ltd. Triggering actions with captured input in a mixed media environment
US8838591B2 (en) 2005-08-23 2014-09-16 Ricoh Co., Ltd. Embedding hot spots in electronic documents
US7669148B2 (en) 2005-08-23 2010-02-23 Ricoh Co., Ltd. System and methods for portable device for mixed media system
US7885955B2 (en) * 2005-08-23 2011-02-08 Ricoh Co. Ltd. Shared document annotation
US7812986B2 (en) 2005-08-23 2010-10-12 Ricoh Co. Ltd. System and methods for use of voice mail and email in a mixed media environment
US8856108B2 (en) 2006-07-31 2014-10-07 Ricoh Co., Ltd. Combining results of image retrieval processes
US8184155B2 (en) 2007-07-11 2012-05-22 Ricoh Co. Ltd. Recognition and tracking using invisible junctions
US7970171B2 (en) 2007-01-18 2011-06-28 Ricoh Co., Ltd. Synthetic image and video generation from ground truth data
US8144921B2 (en) 2007-07-11 2012-03-27 Ricoh Co., Ltd. Information retrieval using invisible junctions and geometric constraints
US7920759B2 (en) 2005-08-23 2011-04-05 Ricoh Co. Ltd. Triggering applications for distributed action execution and use of mixed media recognition as a control input
US8156116B2 (en) * 2006-07-31 2012-04-10 Ricoh Co., Ltd Dynamic presentation of targeted information in a mixed media reality recognition system
US8005831B2 (en) 2005-08-23 2011-08-23 Ricoh Co., Ltd. System and methods for creation and use of a mixed media environment with geographic location information
US8276088B2 (en) 2007-07-11 2012-09-25 Ricoh Co., Ltd. User interface for three-dimensional navigation
US8332401B2 (en) 2004-10-01 2012-12-11 Ricoh Co., Ltd Method and system for position-based image matching in a mixed media environment
US8156427B2 (en) 2005-08-23 2012-04-10 Ricoh Co. Ltd. User interface for mixed media reality
US9171202B2 (en) 2005-08-23 2015-10-27 Ricoh Co., Ltd. Data organization and access for mixed media document system
US8385589B2 (en) 2008-05-15 2013-02-26 Berna Erol Web-based content detection in images, extraction and recognition
US8949287B2 (en) 2005-08-23 2015-02-03 Ricoh Co., Ltd. Embedding hot spots in imaged documents
US9530050B1 (en) 2007-07-11 2016-12-27 Ricoh Co., Ltd. Document annotation sharing
US8369655B2 (en) 2006-07-31 2013-02-05 Ricoh Co., Ltd. Mixed media reality recognition using multiple specialized indexes
US8086038B2 (en) 2007-07-11 2011-12-27 Ricoh Co., Ltd. Invisible junction features for patch recognition
US9373029B2 (en) 2007-07-11 2016-06-21 Ricoh Co., Ltd. Invisible junction feature recognition for document security or annotation
US8195659B2 (en) * 2005-08-23 2012-06-05 Ricoh Co. Ltd. Integration and use of mixed media documents
US8868555B2 (en) 2006-07-31 2014-10-21 Ricoh Co., Ltd. Computation of a recongnizability score (quality predictor) for image retrieval
JP4471812B2 (en) * 2004-10-27 2010-06-02 株式会社リコー Image forming apparatus and printing system
US20060218185A1 (en) * 2005-03-22 2006-09-28 Data Builder, Inc. Construction document management system
US7570816B2 (en) * 2005-03-31 2009-08-04 Microsoft Corporation Systems and methods for detecting text
WO2006107347A2 (en) * 2005-03-31 2006-10-12 Lehman Brothers Inc. System and method for grouping a collection of documents using document series
US7526129B2 (en) * 2005-06-23 2009-04-28 Microsoft Corporation Lifting ink annotations from paper
US7607079B2 (en) * 2005-07-08 2009-10-20 Bruce Reiner Multi-input reporting and editing tool
US7831913B2 (en) * 2005-07-29 2010-11-09 Microsoft Corporation Selection-based item tagging
CA2614364C (en) 2005-08-11 2016-09-27 Contextweb, Inc. Method and system for placement and pricing of internet-based advertisements or services
US7769772B2 (en) 2005-08-23 2010-08-03 Ricoh Co., Ltd. Mixed media reality brokerage network with layout-independent recognition
JP4802672B2 (en) * 2005-11-14 2011-10-26 株式会社日立製作所 Electronic document management apparatus, electronic document management program, electronic document management system
US20070150802A1 (en) * 2005-12-12 2007-06-28 Canon Information Systems Research Australia Pty. Ltd. Document annotation and interface
US8181103B2 (en) * 2005-12-29 2012-05-15 Microsoft Corporation Annotation detection and anchoring on ink notes
US20090012903A1 (en) * 2006-01-26 2009-01-08 Contextweb, Inc. Online exchange for internet ad media
US7836390B2 (en) * 2006-01-26 2010-11-16 Microsoft Corporation Strategies for processing annotations
US7970763B2 (en) * 2006-02-21 2011-06-28 Microsoft Corporation Searching and indexing of photos based on ink annotations
US20070212507A1 (en) * 2006-03-13 2007-09-13 Arst Kevin M Document Flagging And Indexing System
JP4728860B2 (en) 2006-03-29 2011-07-20 株式会社東芝 Information retrieval device
US7646940B2 (en) * 2006-04-04 2010-01-12 Microsoft Corporation Robust indexing and retrieval of electronic ink
GB0607294D0 (en) * 2006-04-11 2006-05-24 Nokia Corp A node
US8027549B2 (en) * 2006-06-12 2011-09-27 D&S Consultants, Inc. System and method for searching a multimedia database using a pictorial language
US7869657B2 (en) * 2006-06-12 2011-01-11 D & S Consultants, Inc. System and method for comparing images using an edit distance
US7870140B2 (en) * 2006-06-12 2011-01-11 D&S Consultants, Inc. System and method of incorporating user preferences in image searches
US8201076B2 (en) 2006-07-31 2012-06-12 Ricoh Co., Ltd. Capturing symbolic information from documents upon printing
US8073263B2 (en) 2006-07-31 2011-12-06 Ricoh Co., Ltd. Multi-classifier selection and monitoring for MMR-based image recognition
US8489987B2 (en) 2006-07-31 2013-07-16 Ricoh Co., Ltd. Monitoring and analyzing creation and usage of visual content using image and hotspot interaction
US9020966B2 (en) 2006-07-31 2015-04-28 Ricoh Co., Ltd. Client device for interacting with a mixed media reality recognition system
US9176984B2 (en) 2006-07-31 2015-11-03 Ricoh Co., Ltd Mixed media reality retrieval of differentially-weighted links
US8676810B2 (en) 2006-07-31 2014-03-18 Ricoh Co., Ltd. Multiple index mixed media reality recognition using unequal priority indexes
US9063952B2 (en) 2006-07-31 2015-06-23 Ricoh Co., Ltd. Mixed media reality recognition with image tracking
US7606752B2 (en) 2006-09-07 2009-10-20 Yodlee Inc. Host exchange in bill paying services
EP2067119A2 (en) 2006-09-08 2009-06-10 Exbiblio B.V. Optical scanners, such as hand-held optical scanners
US20100095009A1 (en) * 2006-10-02 2010-04-15 Nokia Corporation Method, System, and Devices for Network Sharing or Searching Of Resources
US8798988B1 (en) * 2006-10-24 2014-08-05 Google Inc. Identifying related terms in different languages
US8041730B1 (en) 2006-10-24 2011-10-18 Google Inc. Using geographic data to identify correlated geographic synonyms
US8654973B2 (en) * 2006-11-22 2014-02-18 International Business Machines Corporation Method, system, and program product for encrypting portions of a document using selective annotation
US20080123901A1 (en) * 2006-11-29 2008-05-29 D&S Consultants, Inc. Method and System for Comparing Images Using a Pictorial Edit Distance
US8311341B1 (en) 2006-11-29 2012-11-13 D & S Consultants, Inc. Enhanced method for comparing images using a pictorial edit distance
US8504546B2 (en) * 2006-11-29 2013-08-06 D&S Consultants, Inc. Method and system for searching multimedia content
US7921120B2 (en) 2006-11-30 2011-04-05 D&S Consultants Method and system for image recognition using a similarity inverse matrix
US7773811B2 (en) * 2006-12-06 2010-08-10 D & S Consultants, Inc. Method and system for searching a database of graphical data
US8661012B1 (en) 2006-12-29 2014-02-25 Google Inc. Ensuring that a synonym for a query phrase does not drop information present in the query phrase
US7925498B1 (en) 2006-12-29 2011-04-12 Google Inc. Identifying a synonym with N-gram agreement for a query phrase
US20080172380A1 (en) * 2007-01-17 2008-07-17 Wojciech Czyz Information retrieval based on information location in the information space.
US7890521B1 (en) * 2007-02-07 2011-02-15 Google Inc. Document-based synonym generation
US8347206B2 (en) 2007-03-15 2013-01-01 Microsoft Corporation Interactive image tagging
US20080235597A1 (en) * 2007-03-19 2008-09-25 Mor Schlesinger Systems and methods of data integration for creating custom books
US7895518B2 (en) * 2007-04-27 2011-02-22 Shapewriter Inc. System and method for preview and selection of words
WO2008133619A2 (en) * 2007-04-27 2008-11-06 Shapewriter Inc. System and method for preview and selection of words
US8094939B2 (en) * 2007-06-26 2012-01-10 Microsoft Corporation Digital ink-based search
US8041120B2 (en) * 2007-06-26 2011-10-18 Microsoft Corporation Unified digital ink recognition
US8315482B2 (en) * 2007-06-26 2012-11-20 Microsoft Corporation Integrated platform for user input of digital ink
US8190627B2 (en) * 2007-06-28 2012-05-29 Microsoft Corporation Machine assisted query formulation
US20090013044A1 (en) * 2007-07-05 2009-01-08 Microsoft Corporation Techniques for managing annotation transformations for context changes
US8037086B1 (en) 2007-07-10 2011-10-11 Google Inc. Identifying common co-occurring elements in lists
US8001136B1 (en) 2007-07-10 2011-08-16 Google Inc. Longest-common-subsequence detection for common synonyms
US20090018994A1 (en) * 2007-07-12 2009-01-15 Honeywell International, Inc. Time series data complex query visualization
US8122022B1 (en) 2007-08-10 2012-02-21 Google Inc. Abbreviation detection for common synonym generation
US10762080B2 (en) * 2007-08-14 2020-09-01 John Nicholas and Kristin Gross Trust Temporal document sorter and method
US8638363B2 (en) 2009-02-18 2014-01-28 Google Inc. Automatically capturing information, such as capturing information using a document-aware device
US8165404B2 (en) * 2007-09-19 2012-04-24 Ricoh Company, Ltd. Method and apparatus for creating document data, and computer program product
US7814054B2 (en) * 2008-04-03 2010-10-12 Laurion James E System and method for providing common operators across multiple applications
US8261334B2 (en) 2008-04-25 2012-09-04 Yodlee Inc. System for performing web authentication of a user by proxy
US9209975B2 (en) * 2008-10-15 2015-12-08 Ricoh Company, Ltd. Secure access of electronic documents and data from client terminal
CA2736619A1 (en) * 2008-07-22 2010-01-28 Contextweb, Inc. New open insertion order system to interface with an exchange for internet ad media
US9275684B2 (en) * 2008-09-12 2016-03-01 At&T Intellectual Property I, L.P. Providing sketch annotations with multimedia programs
US8555359B2 (en) 2009-02-26 2013-10-08 Yodlee, Inc. System and methods for automatically accessing a web site on behalf of a client
DE202010018551U1 (en) 2009-03-12 2017-08-24 Google, Inc. Automatically deliver content associated with captured information, such as information collected in real-time
US8447066B2 (en) 2009-03-12 2013-05-21 Google Inc. Performing actions based on capturing information from rendered documents, such as documents under copyright
US20100325557A1 (en) * 2009-06-17 2010-12-23 Agostino Sibillo Annotation of aggregated content, systems and methods
US8385660B2 (en) 2009-06-24 2013-02-26 Ricoh Co., Ltd. Mixed media reality indexing and retrieval for repeated content
US8306329B2 (en) * 2009-08-17 2012-11-06 Indian Institute Of Science System and method for searching handwritten texts
KR101660271B1 (en) * 2009-08-21 2016-10-11 삼성전자주식회사 Metadata tagging system, image searching method, device, and method for tagging gesture
US8186436B2 (en) * 2009-09-10 2012-05-29 Warren Carlos Thermal insulating packer fluid
TW201118619A (en) * 2009-11-30 2011-06-01 Inst Information Industry An opinion term mining method and apparatus thereof
JP5617233B2 (en) * 2009-11-30 2014-11-05 ソニー株式会社 Information processing apparatus, information processing method, and program thereof
US9081799B2 (en) 2009-12-04 2015-07-14 Google Inc. Using gestalt information to identify locations in printed information
US9323784B2 (en) 2009-12-09 2016-04-26 Google Inc. Image search using text-based elements within the contents of images
JP5589466B2 (en) * 2010-03-17 2014-09-17 ソニー株式会社 Information processing apparatus, program, recording medium, and information processing system
US20120005183A1 (en) * 2010-06-30 2012-01-05 Emergency24, Inc. System and method for aggregating and interactive ranking of search engine results
US8918734B2 (en) 2010-07-28 2014-12-23 Nuance Communications, Inc. Reduced keyboard with prediction solutions when input is a partial sliding trajectory
JP5672830B2 (en) * 2010-08-06 2015-02-18 株式会社リコー Image display control device, image display system, image display method, program, and recording medium
JP5012981B2 (en) * 2010-09-09 2012-08-29 カシオ計算機株式会社 Electronic dictionary device and program
US8718375B2 (en) * 2010-12-03 2014-05-06 Massachusetts Institute Of Technology Sketch recognition system
JP5742378B2 (en) * 2011-03-30 2015-07-01 ソニー株式会社 Information processing apparatus, playlist generation method, and playlist generation program
US9058331B2 (en) 2011-07-27 2015-06-16 Ricoh Co., Ltd. Generating a conversation in a social network based on visual search results
CA2870362C (en) 2012-04-11 2017-03-21 Blackberry Limited Systems and methods for searching for analog notations and annotations
JP5717691B2 (en) * 2012-05-28 2015-05-13 株式会社東芝 Handwritten character search device, method and program
JP2013246732A (en) 2012-05-28 2013-12-09 Toshiba Corp Handwritten character retrieval apparatus, method and program
US8487895B1 (en) * 2012-06-26 2013-07-16 Google Inc. Systems and methods for enhancing touch event processing performance
US11270058B2 (en) * 2012-11-29 2022-03-08 Red Hat, Inc. Referencing a portion of a document
US9558400B2 (en) * 2013-03-07 2017-01-31 Ricoh Company, Ltd. Search by stroke
JP5735126B2 (en) * 2013-04-26 2015-06-17 株式会社東芝 System and handwriting search method
CN104346388B (en) * 2013-07-31 2018-03-09 株式会社理光 Cloud server and Image Storage Retrieval system
US9418281B2 (en) * 2013-12-30 2016-08-16 Google Inc. Segmentation of overwritten online handwriting input
JP6092462B2 (en) * 2014-03-12 2017-03-08 株式会社東芝 Electronic device, method and program
JP2016110389A (en) * 2014-12-05 2016-06-20 株式会社東芝 Searcher, method and program
US10635413B1 (en) 2018-12-05 2020-04-28 Bank Of America Corporation System for transforming using interface image segments and constructing user interface objects
US10678521B1 (en) 2018-12-05 2020-06-09 Bank Of America Corporation System for image segmentation, transformation and user interface component construction
US11328796B1 (en) 2020-02-25 2022-05-10 Vignet Incorporated Techniques for selecting cohorts for decentralized clinical trials for pharmaceutical research
US11605038B1 (en) 2020-05-18 2023-03-14 Vignet Incorporated Selecting digital health technology to achieve data collection compliance in clinical trials
US11461216B1 (en) 2020-05-18 2022-10-04 Vignet Incorporated Monitoring and improving data collection using digital health technology
US11527329B2 (en) 2020-07-28 2022-12-13 Xifin, Inc. Automatically determining a medical recommendation for a patient based on multiple medical images from multiple different medical imaging modalities
US11296971B1 (en) 2021-02-03 2022-04-05 Vignet Incorporated Managing and adapting monitoring programs
US11521714B1 (en) 2021-02-03 2022-12-06 Vignet Incorporated Increasing diversity of participants in health research using adaptive methods
US11789837B1 (en) 2021-02-03 2023-10-17 Vignet Incorporated Adaptive data collection in clinical trials to increase the likelihood of on-time completion of a trial
US11196656B1 (en) 2021-02-03 2021-12-07 Vignet Incorporated Improving diversity in cohorts for health research
US11361846B1 (en) 2021-02-03 2022-06-14 Vignet Incorporated Systems and methods for customizing monitoring programs involving remote devices
US11316941B1 (en) 2021-02-03 2022-04-26 Vignet Incorporated Remotely managing and adapting monitoring programs using machine learning predictions

Family Cites Families (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0750483B2 (en) * 1985-05-22 1995-05-31 株式会社日立製作所 How to store additional information about document images
US4972496A (en) * 1986-07-25 1990-11-20 Grid Systems Corporation Handwritten keyboardless entry computer system
US5194852A (en) * 1986-12-01 1993-03-16 More Edward S Electro-optic slate for direct entry and display and/or storage of hand-entered textual and graphic information
JP2735187B2 (en) * 1987-03-17 1998-04-02 株式会社東芝 Information search method
JPS63233427A (en) * 1987-03-20 1988-09-29 Hitachi Ltd Method and apparatus for detecting approximate pattern
EP0374241B1 (en) * 1988-05-27 1997-08-27 Kodak Limited Document annotation and manipulation in a data processing system
US5038382A (en) * 1989-10-13 1991-08-06 International Business Machines Corporation Multi-scale recognizer for hand drawn strokes
US5220649A (en) * 1991-03-20 1993-06-15 Forcier Mitchell D Script/binary-encoded-character processing method and system with moving space insertion mode
US5313527A (en) * 1991-06-07 1994-05-17 Paragraph International Method and apparatus for recognizing cursive writing from sequential input information
US5455901A (en) * 1991-11-12 1995-10-03 Compaq Computer Corporation Input device with deferred translation
US5434777A (en) * 1992-05-27 1995-07-18 Apple Computer, Inc. Method and apparatus for processing natural language
US5463696A (en) * 1992-05-27 1995-10-31 Apple Computer, Inc. Recognition system and method for user inputs to a computer system
US5325475A (en) * 1992-09-09 1994-06-28 Massachusetts Institute Of Technology Computer method and apparatus for matching between line drawings
US5583950A (en) * 1992-09-16 1996-12-10 Mikos, Ltd. Method and apparatus for flash correlation
TW401567B (en) * 1992-10-09 2000-08-11 Matsushita Electric Ind Co Ltd Certifiable optical character recognition
US5666139A (en) * 1992-10-15 1997-09-09 Advanced Pen Technologies, Inc. Pen-based computer copy editing apparatus and method for manuscripts
US5579471A (en) * 1992-11-09 1996-11-26 International Business Machines Corporation Image query system and method
JPH06231171A (en) * 1993-02-03 1994-08-19 Hitachi Ltd Document retrieving device and pen base computing system
JPH0773190A (en) * 1993-04-29 1995-03-17 Matsushita Electric Ind Co Ltd Pictograph naming for pen base computer system
US5613019A (en) * 1993-05-20 1997-03-18 Microsoft Corporation System and methods for spacing, storing and recognizing electronic representations of handwriting, printing and drawings
US5592608A (en) * 1993-10-15 1997-01-07 Xerox Corporation Interactively producing indices into image and gesture-based data using unrecognized graphical objects
JPH07319924A (en) * 1994-05-24 1995-12-08 Matsushita Electric Ind Co Ltd Indexing and searching method for electronic handwritten document
US5687254A (en) * 1994-06-06 1997-11-11 Xerox Corporation Searching and Matching unrecognized handwriting
EP0691623B1 (en) * 1994-07-04 2001-10-04 Hewlett-Packard Company, A Delaware Corporation Scribble matching
US5600775A (en) * 1994-08-26 1997-02-04 Emotion, Inc. Method and apparatus for annotating full motion video and other indexed data structures
JP3535624B2 (en) * 1995-09-21 2004-06-07 キヤノン株式会社 Search device and method

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014075174A1 (en) * 2012-11-19 2014-05-22 Imds America Inc. Method and system for the spotting of arbitrary words in handwritten documents

Also Published As

Publication number Publication date
DE69731418D1 (en) 2004-12-09
US5832474A (en) 1998-11-03
DE69731418T2 (en) 2005-11-10
EP0791883A2 (en) 1997-08-27
EP0791883B1 (en) 2004-11-03
EP0791883A3 (en) 1999-01-07
JPH1055371A (en) 1998-02-24

Similar Documents

Publication Publication Date Title
US5832474A (en) Document search and retrieval system with partial match searching of user-drawn annotations
US5734882A (en) Pictographic bitmap naming of files in pen-based computer systems
EP0539106B1 (en) Electronic information delivery system
EP0731948B8 (en) Method and apparatus for synchronizing, displaying and manipulating text and image documents
US5933823A (en) Image database browsing and query using texture analysis
US5950214A (en) System, method, and computer program product for accessing a note database having subnote information for the purpose of manipulating subnotes linked to portions of documents
US6018749A (en) System, method, and computer program product for generating documents using pagination information
JP4260790B2 (en) Filing / retrieval apparatus and filing / retrieval method
US6766494B1 (en) Method and system for creating ad-hoc links from free-form ink
US6442578B1 (en) Script character processing method for compression encoding and smoothing of ink strokes
US5903904A (en) Iconic paper for alphabetic, japanese and graphic documents
US5590257A (en) Script character processing method and system with bit-mapped document editing
US8532384B2 (en) Method of retrieving information from a digital image
US6434581B1 (en) Script character processing method for interactively adjusting space between writing element
JPH07182445A (en) Method for decision of important correspondence for computation processing
JPH08180068A (en) Electronic filing device
JPH03276260A (en) Electronic filing device containing title processing function for character code
JP3841318B2 (en) Icon generation method, document search method, and document server
Coustaty et al. Augmented documents for research contact management
JPS63293674A (en) Retrieving/displaying method for sentence
JPH08202859A (en) Electronic filing device and its method
AU712181B2 (en) Method and apparatus for synchronizing, displaying and manipulating text and image documents
JPS63223964A (en) Retrieving device
JPS60256853A (en) Method and device for file retrieval
JPH0927009A (en) Device and method for character recognition

Legal Events

Date Code Title Description
EEER Examination request
FZDE Discontinued