US20030194130A1 - Handwriting recognition method and apparatus having multiple selectable dictionaries - Google Patents
Handwriting recognition method and apparatus having multiple selectable dictionaries Download PDFInfo
- Publication number
- US20030194130A1 US20030194130A1 US09/524,064 US52406400A US2003194130A1 US 20030194130 A1 US20030194130 A1 US 20030194130A1 US 52406400 A US52406400 A US 52406400A US 2003194130 A1 US2003194130 A1 US 2003194130A1
- Authority
- US
- United States
- Prior art keywords
- information
- handwritten input
- dictionaries
- recognition
- recognition data
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/24—Character recognition characterised by the processing or recognition method
- G06V30/242—Division of the character sequences into groups prior to recognition; Selection of dictionaries
Definitions
- This invention relates generally to the field of handwriting recognition, and more particularly to handwriting recognition data templates used in handwriting recognition systems.
- Handwriting recognition programs generally operate by comparing data generated from handwritten words or characters to stored recognition data (referred to as a dictionary by those skilled in the art) in an attempt to correctly replicate the handwritten words or characters as typewritten text.
- a dictionary stored recognition data
- the trend has been to increase the size of the dictionary to make the recognition program more general in nature so as to be universally useful in various applications.
- FIG. 1 is a perspective view of a computing device in accordance with the present invention
- FIG. 2 is an exemplary block diagram of the computing device of FIG. 1;
- FIG. 3 is a graphic diagram illustrating an exemplary software program configuration of the device of FIG. 1 in accordance with the present invention
- FIG. 4 is a block diagram of the exemplary recognition program of FIG. 3 that may be used in accordance with the present invention.
- FIG. 5 is an illustration of the organization of the recognition data in accordance with the present invention.
- FIG. 6 is an exemplary illustration depicting an optional embodiment included weighted recognition data in accordance with the present invention.
- FIG. 7, FIG. 8, and FIG. 9 are flow diagrams illustrating a preferred method in accordance with the present invention.
- FIG. 10 is an illustration of an optional signature embodiment in accordance with the present invention.
- FIG. 1 and FIG. 2 illustrate a computing device 2 suitable for use with the present invention.
- the computer device 2 may be, for example, a Thinkpad lap-top type computer made by IBM. Alternately, a personal digital assistant, such as the Newton manufactured by Apple Computer, or the Envoy wireless communicator, made by Motorola, or similar computing devices could be employed with the present invention.
- the computing device 2 includes a digitizing display 4 that may be used as an alternate to the keyboard 6 to input information by using a stylus 8 to select functions, enter instructions, or handwritten text, graphics, or other information onto the display 4 .
- contemporary computing devices typically include a processing component 12 such as a microprocessor or digital signal processor that, together with other general circuitry, execute the instructions of one or more software programs residing in a memory 14 that may include an operating system to control the finctionality and operation of the computing device 2 .
- a conventional digitizing tablet 16 may be used to enter printed or handwritten words or text allowing a conventional (non-digitizing or non-touch sensitive) display to be employed for the display 4 .
- a wireless modem (radio) 17 for transmitting, receiving, or transceiving information such as the Envoy wireless communicator is capable of doing.
- the display 4 may be seen to present a graphic user interface commonly referred to by those skilled in the art as a window 10 .
- the window 10 is associated with a computer application program or other computer program, and it is know for the particular association between a window and computer program to be displayed to the user via providing the name or identification of the computer program in an area of the window referred to as a title bar 18 .
- certain user commands or instructions are given to the computer program via user selection of one or more icons 20 that ordinarily reside in a area of the graphic user interface know as a toolbar 22 by those skilled in the art.
- the window 10 includes several fields 24 - 32 for receiving user handwriting via the stylus 8 .
- the recognition system comprises several dictionaries containing recognition data (with or without weighting).
- the present invention contains the size of any particular dictionary to a point that does not compromise recognition accuracy, but offers more universal application via selectively activating sets of dictionaries as appropriate for the application.
- the user may select which dictionaries are active for use by the recognition system.
- appropriate sets of dictionaries are automatically activated by the user handwriting in a particular field 24 - 32 of the window 10 .
- FIG. 3 illustrates a software program arrangement in accordance with the present invention to enable the computing device 2 of FIG. 1 to utilize the present invention.
- Overall control of the computing device is governed by an operating system 34 .
- Typical operating systems includes utility programs 36 and input/output (I/O) 38 control, and generally interfaces with other software programs ( 40 - 46 ) via an application programming interface (API) 38 .
- API application programming interface
- a software program 40 for recognizing handwritten user input resides above the API layer and includes instructions and data to implement printing and/or cursive handwriting recognition.
- the present invention can be understood generally with reference to FIG. 1 through FIG. 4 in that a user could handwrite text (for example) onto the display 4 via the stylus 8 .
- the user's handwritten input is electronically displayed (which is referred to by those skilled in the art as “ink”) in the window 10 (which in this example is associated with a handwriting recognition program).
- the I/O control portion 38 of the operating system 34 digitizes the handwriting (ink) via known techniques and sends information representing the handwritten input to the handwriting recognition program 40 via the API 48 .
- the computing device 2 executes the functionality of any known handwriting recognition engine 50 and operates to compare the information representing the handwritten input with all or a selected set of a plurality dictionaries that contain stored recognition data 52 .
- the recognition data (commonly referred to by those skilled in the art as templates) is processed with the information representing the user handwritten input.
- the output of the recognition engine 46 is a list of candidate recognition information that, if correctly recognized, replicates the handwritten input as typewritten text on the display 4 and may be transferred, passed, or sent from the recognition program 40 to one of the other application programs (such as a word processing program).
- FIG. 5 illustrates a preferred multiple dictionary arrangement for the recognition data 52 arrangement in accordance with the present invention.
- the recognition data 52 comprises a plurality of dictionaries 54 - 60 that are selectively activated by the user or automatically by the recognition program 40 .
- a set 62 of the dictionaries 54 - 58 might be activated.
- the set of dictionaries 64 could be activated, while writing in the field 28 might automatically activate set 66 of dictionaries 56 and 58 .
- one of the dictionaries can be added to by the user so that certain proper names, acronyms, and other words not contained in the other dictionaries can be added for use by the recognition system.
- the other dictionaries are preferably divided into general and specialty areas such as: U.S. State Names; Prescription Drug Names; Over-the-counter Drugs; City or County Names; Historical Names, Events, or Places; Medical Terms (or medial specialties such as optometry) Legal Terms (or legal specialties such as patent law); U.S. President Names; a Main Dictionary (that may be generally active with selected other dictionaries); or only Numbers.
- the dictionaries are data stored in a memory ( 14 of FIG. 2), additional dictionaries may be added or replaced by the user.
- FIG. 6 is an exemplary illustration of dictionary 58 in the form of a table that is preferably stored in memory ( 14 in FIG. 2) components of the computing device.
- the dictionary 58 includes a plurality of data templates 68 each having a weighting value 70 associated therewith.
- Any known data association technique e.g., vectors, pointers, tables, or appending data
- the present invention contemplates that only certain of the data templates, such as, for example, the data templates known to cause the most recognition errors, could have an associated weighting value.
- the weighting values 70 are used by the recognition engine ( 50 in FIG. 4) via established practices to enhance the likelihood that the candidate recognition information correctly replicates the handwritten input.
- templates for a handwritten word may reside in multiple of the dictionaries some having differing weighting values depending upon the dictionary.
- the city name “Chicago” may have a relative high weighting value in a City Name dictionary as compared to the Main dictionary, which left to itself my recognize that handwritten city name as “Chicago”.
- the recognizer returns only the word associated with the template having the highest weighting value from the various active dictionaries as the candidate recognition information for presentation to the user. This permits other candidate words to be presented to the user in an editing mode should a recognition error be made due to poor handwriting or other causes.
- FIG. 7, FIG. 8, and FIG. 9 are flow diagrams that, together with FIG. 1, illustrate the preferred method of the present invention.
- the field receiving the input (assuming more that one field is used) is determined (step 82 ) and the set of dictionaries associated with that field are activated in step 84 (or the user selected set in the one field case).
- Decision 86 determines whether the user has instructed that the handwritten input be processed such as by the user selecting a particular icon 20 from the toolbar 22 . If recognition has not been user initiated, decision 88 determines whether a time interval has elapsed from the conclusion of input (referred to as pen-up by those skilled in the art).
- decision 90 determines whether the user has started handwriting input in another field, from which an inference is drawn that the input in the prior field is complete and can be applied to the recognition system.
- An affirmative determination from decision 90 stores the new input (step 92 ) after which, and in the case of affirmative determinations from decisions 86 or 88 , the input is applied to the recognizer for processing with the active dictionaries in step 94 .
- decision 96 optionally determines whether the field receiving the input has special presentation or display parameters associated with it. For example, a field might be selected by a user to present recognized text in all capital letters. A field associated with telephone numbers could automatically group numbers for area code and prefix and insert dashes (“-”) in between. If special presentation formats are not used, the recognized text is presented to the user (step 100 ), however, the present invention contemplates an optional step 102 wherein the recognized text or character might be expanded to form complete words for phrases preset by the user or contained in a dictionary. For example a check character ( ⁇ square root ⁇ ) or a “Y” can be expanded to “Yes”, while a “N” or dash character (“-”) can be expanded to “No”. In a medical application, recognized text such as “Tyl 350 2 ⁇ ” could be expanded to “Tylenol 350 mg Take Twice A Day”.
- step 104 cross-references text recognized in one field to known associated text in other fields.
- a client or patient name can be cross-referenced to the associated client or patient number and/or case number or chart number.
- Address and phone numbers can be automatically completed in the appropriate fields. Further examples range from relative simple phone/address book applications where the fields can include: Name field; Address field; City field; State field; Zip Code field; and Phone Number field.
- a more complicated application includes medical applications where the fields can include: Name field; Patient Number field; Drug field; Drug strength field; Frequency (of taking medication) field; Refill field; and General Instruction field.
- Legal applications are also contemplated where the field can include: Client Name field; Client Number field; Matter Number field; Other Party field; Other Firm field; Other Counsel field; Contact Information field; and Issues field.
- decision 106 determines whether any user input was stored in 92 indicating that more input remains to be recognized. If so, the flow returns to step 82 to determine the field in which the stored text was entered and the flow proceeds for activating appropriate dictionaries and recognizing the text as described above. Conversely however, if no stored input remains to be recognized, decision 108 determines whether the user desires to edit any recognition errors in the recognized text such as by selecting a particular icon 20 in FIG. 1. If so, errors may be corrected using any known technique, the present invention contemplates the editing method used not offer as alternative words the same words from other dictionaries as described above in conjunction with FIG. 6.
- decision 112 determines whether the user desires to append an optional signature or other information to the recognized text as a measure of authentication.
- This alternate embodiment is particularly useful with the present invention in a medical application such as to authenticate a prescription from a medical doctor. If a signature is desired, it is appended in step 114 to the text or into a signature field.
- Decision 116 determines whether the optional wireless modem ( 17 in FIG. 2) is used in the application of the present invention such as to transmit a prescription to a pharmacy to be filled for a patient. If so, the information (with our without the signature) is transmitted in step 118 prior to returning to FIG. 7 to await further input from the user.
- FIG. 10 illustrates an alternate preferred embodiment for optionally entering a personal signature or other symbol to be used as authentication information according to the present invention.
- An authentication or signature mode can be selected for example by the user selecting a particular icon 20 in the tool bar 22 of FIG. 1.
- a graphical image (window) 120 is presented to the user on the display 4 of the computing device 2 of FIG. 1.
- the graphical image 120 includes a signature area 122 and may also include a command (tool bar) area 124 that includes several icons 126 - 130 used to affect editing or other functions and a status area 132 used to convey information to the user.
- the signature “William Smith” has been handwritten in the signature area 124 to be stored and later appended to other handwritten input or sent to other application programs ( 34 - 38 in FIG. 3) for the convenience of the user.
- the signature “ink” is not applied to the recognizer, but rather, is stored as information representing the “ink” to be used, for example, by a doctor to authenticate a drug prescription.
- the present invention provides significant flexibility to handwriting recognition programs by activating selective sets of multiple specialized or general recognition dictionaries as described above.
- Several optional features of the present invention offer significant advantages for use in a wide variety of applications.
- Further optional variants of the present invention include the user of multiple windows (pages) that each may have one or more fields and having the active sets of dictionaries change depending upon which page (window) is being displayed to the user.
- the recognition engine used to process the handwritten input with the active dictionaries may change depending upon the input field or window. In this regard, some fields may utilized a printed character handwriting recognizer while other field may employ a cursive handwriting recognition engine.
Abstract
Description
- This invention relates generally to the field of handwriting recognition, and more particularly to handwriting recognition data templates used in handwriting recognition systems.
- Handwriting recognition programs generally operate by comparing data generated from handwritten words or characters to stored recognition data (referred to as a dictionary by those skilled in the art) in an attempt to correctly replicate the handwritten words or characters as typewritten text. As commercial applications for handwriting recognition become more prominent in the marketplace, the trend has been to increase the size of the dictionary to make the recognition program more general in nature so as to be universally useful in various applications.
- However, continually increasing the size of the dictionary can lead to diminishing returns in the context of reduced recognition accuracy. Also, a large dictionary can lead to increased recognition processing, which manifests itself to the user as a slower recognition response time. Some more advanced handwriting recognition programs have attempted (with mixed results) to compensate for a large recognition dictionary by including weighting values associated with some or all of the stored recognition data that are used in the recognition process to improve the likelihood of correctly recognizing the handwritten input.
- Nevertheless, there exists a need for a handwriting recognition system that may find wide application without compromising recognition accuracy and speed.
- FIG. 1 is a perspective view of a computing device in accordance with the present invention;
- FIG. 2 is an exemplary block diagram of the computing device of FIG. 1;
- FIG. 3 is a graphic diagram illustrating an exemplary software program configuration of the device of FIG. 1 in accordance with the present invention;
- FIG. 4 is a block diagram of the exemplary recognition program of FIG. 3 that may be used in accordance with the present invention;
- FIG. 5 is an illustration of the organization of the recognition data in accordance with the present invention;
- FIG. 6 is an exemplary illustration depicting an optional embodiment included weighted recognition data in accordance with the present invention;
- FIG. 7, FIG. 8, and FIG. 9 are flow diagrams illustrating a preferred method in accordance with the present invention;
- FIG. 10 is an illustration of an optional signature embodiment in accordance with the present invention.
- FIG. 1 and FIG. 2 illustrate a
computing device 2 suitable for use with the present invention. Thecomputer device 2 may be, for example, a Thinkpad lap-top type computer made by IBM. Alternately, a personal digital assistant, such as the Newton manufactured by Apple Computer, or the Envoy wireless communicator, made by Motorola, or similar computing devices could be employed with the present invention. As shown in FIG. 1, thecomputing device 2 includes adigitizing display 4 that may be used as an alternate to thekeyboard 6 to input information by using astylus 8 to select functions, enter instructions, or handwritten text, graphics, or other information onto thedisplay 4. - As is known, contemporary computing devices typically include a
processing component 12 such as a microprocessor or digital signal processor that, together with other general circuitry, execute the instructions of one or more software programs residing in amemory 14 that may include an operating system to control the finctionality and operation of thecomputing device 2. Optionally, a conventionaldigitizing tablet 16 may be used to enter printed or handwritten words or text allowing a conventional (non-digitizing or non-touch sensitive) display to be employed for thedisplay 4. Another option comprises a wireless modem (radio) 17 for transmitting, receiving, or transceiving information such as the Envoy wireless communicator is capable of doing. - Referring to FIG. 1, the
display 4 may be seen to present a graphic user interface commonly referred to by those skilled in the art as awindow 10. Thewindow 10 is associated with a computer application program or other computer program, and it is know for the particular association between a window and computer program to be displayed to the user via providing the name or identification of the computer program in an area of the window referred to as atitle bar 18. Generally, certain user commands or instructions are given to the computer program via user selection of one ormore icons 20 that ordinarily reside in a area of the graphic user interface know as atoolbar 22 by those skilled in the art. - As can be seen in FIG. 1, the
window 10 includes several fields 24-32 for receiving user handwriting via thestylus 8. In the present invention, one field may be used or any number of fields may be used according to the application. According to the present invention, the recognition system comprises several dictionaries containing recognition data (with or without weighting). The present invention contains the size of any particular dictionary to a point that does not compromise recognition accuracy, but offers more universal application via selectively activating sets of dictionaries as appropriate for the application. In one embodiment, the user may select which dictionaries are active for use by the recognition system. In another embodiment, appropriate sets of dictionaries are automatically activated by the user handwriting in a particular field 24-32 of thewindow 10. - FIG. 3 illustrates a software program arrangement in accordance with the present invention to enable the
computing device 2 of FIG. 1 to utilize the present invention. Overall control of the computing device is governed by anoperating system 34. Typical operating systems includesutility programs 36 and input/output (I/O) 38 control, and generally interfaces with other software programs (40-46) via an application programming interface (API) 38. In the preferred embodiment of the present invention asoftware program 40 for recognizing handwritten user input resides above the API layer and includes instructions and data to implement printing and/or cursive handwriting recognition. - The present invention can be understood generally with reference to FIG. 1 through FIG. 4 in that a user could handwrite text (for example) onto the
display 4 via thestylus 8. Typically, the user's handwritten input is electronically displayed (which is referred to by those skilled in the art as “ink”) in the window 10 (which in this example is associated with a handwriting recognition program). The I/O control portion 38 of theoperating system 34 digitizes the handwriting (ink) via known techniques and sends information representing the handwritten input to thehandwriting recognition program 40 via theAPI 48. Executing the instructions of the user input recognition program 38 (for example, the Lexicus Longhand cursive handwriting recognition program or the QuickPrint print recognition program, both by the Lexicus Division of Motorola), thecomputing device 2 performs the functionality of any knownhandwriting recognition engine 50 and operates to compare the information representing the handwritten input with all or a selected set of a plurality dictionaries that containstored recognition data 52. Depending upon which dictionaries are active, the recognition data (commonly referred to by those skilled in the art as templates) is processed with the information representing the user handwritten input. The output of therecognition engine 46 is a list of candidate recognition information that, if correctly recognized, replicates the handwritten input as typewritten text on thedisplay 4 and may be transferred, passed, or sent from therecognition program 40 to one of the other application programs (such as a word processing program). - FIG. 5 illustrates a preferred multiple dictionary arrangement for the
recognition data 52 arrangement in accordance with the present invention. As can be seen, therecognition data 52 comprises a plurality of dictionaries 54-60 that are selectively activated by the user or automatically by therecognition program 40. For example, upon detection of a user writing infield 24 ofwindow 10 in FIG. 1, aset 62 of the dictionaries 54-58 might be activated. Also, when the user writes infield 32, the set ofdictionaries 64 could be activated, while writing in thefield 28 might automatically activate set 66 ofdictionaries - According to the invention, one of the dictionaries (60 for example) can be added to by the user so that certain proper names, acronyms, and other words not contained in the other dictionaries can be added for use by the recognition system. The other dictionaries are preferably divided into general and specialty areas such as: U.S. State Names; Prescription Drug Names; Over-the-counter Drugs; City or County Names; Historical Names, Events, or Places; Medical Terms (or medial specialties such as optometry) Legal Terms (or legal specialties such as patent law); U.S. President Names; a Main Dictionary (that may be generally active with selected other dictionaries); or only Numbers. Moreover, since in the preferred embodiment the dictionaries are data stored in a memory (14 of FIG. 2), additional dictionaries may be added or replaced by the user.
- FIG. 6 is an exemplary illustration of
dictionary 58 in the form of a table that is preferably stored in memory (14 in FIG. 2) components of the computing device. In this embodiment, thedictionary 58 includes a plurality ofdata templates 68 each having aweighting value 70 associated therewith. Any known data association technique (e.g., vectors, pointers, tables, or appending data) is suitable for use with the present invention to associate a particular data template with its weighting value. Alternately, the present invention contemplates that only certain of the data templates, such as, for example, the data templates known to cause the most recognition errors, could have an associated weighting value. Theweighting values 70 are used by the recognition engine (50 in FIG. 4) via established practices to enhance the likelihood that the candidate recognition information correctly replicates the handwritten input. - In this alternate embodiment, templates for a handwritten word may reside in multiple of the dictionaries some having differing weighting values depending upon the dictionary. For example the city name “Chicago” may have a relative high weighting value in a City Name dictionary as compared to the Main dictionary, which left to itself my recognize that handwritten city name as “Chicago”. According to the invention, when multiple active dictionaries contain templates for the same word, the recognizer returns only the word associated with the template having the highest weighting value from the various active dictionaries as the candidate recognition information for presentation to the user. This permits other candidate words to be presented to the user in an editing mode should a recognition error be made due to poor handwriting or other causes.
- FIG. 7, FIG. 8, and FIG. 9 are flow diagrams that, together with FIG. 1, illustrate the preferred method of the present invention. Upon detection of input (decision80), the field receiving the input (assuming more that one field is used) is determined (step 82) and the set of dictionaries associated with that field are activated in step 84 (or the user selected set in the one field case).
Decision 86 determines whether the user has instructed that the handwritten input be processed such as by the user selecting aparticular icon 20 from thetoolbar 22. If recognition has not been user initiated,decision 88 determines whether a time interval has elapsed from the conclusion of input (referred to as pen-up by those skilled in the art). If the time interval has not elapsed,decision 90 determines whether the user has started handwriting input in another field, from which an inference is drawn that the input in the prior field is complete and can be applied to the recognition system. An affirmative determination fromdecision 90 stores the new input (step 92) after which, and in the case of affirmative determinations fromdecisions step 94. - After recognition,
decision 96 optionally determines whether the field receiving the input has special presentation or display parameters associated with it. For example, a field might be selected by a user to present recognized text in all capital letters. A field associated with telephone numbers could automatically group numbers for area code and prefix and insert dashes (“-”) in between. If special presentation formats are not used, the recognized text is presented to the user (step 100), however, the present invention contemplates an optional step 102 wherein the recognized text or character might be expanded to form complete words for phrases preset by the user or contained in a dictionary. For example a check character ({square root}) or a “Y” can be expanded to “Yes”, while a “N” or dash character (“-”) can be expanded to “No”. In a medical application, recognized text such as “Tyl 350 2×” could be expanded to “Tylenol 350 mg Take Twice A Day”. - Another option contemplated by the present invention for multiple field applications comprises
step 104 which cross-references text recognized in one field to known associated text in other fields. For example, in a legal or medical application, a client or patient name can be cross-referenced to the associated client or patient number and/or case number or chart number. Address and phone numbers can be automatically completed in the appropriate fields. Further examples range from relative simple phone/address book applications where the fields can include: Name field; Address field; City field; State field; Zip Code field; and Phone Number field. A more complicated application includes medical applications where the fields can include: Name field; Patient Number field; Drug field; Drug strength field; Frequency (of taking medication) field; Refill field; and General Instruction field. Legal applications are also contemplated where the field can include: Client Name field; Client Number field; Matter Number field; Other Party field; Other Firm field; Other Counsel field; Contact Information field; and Issues field. - After the recognized text has been present using any of the various options contemplated by the present invention,
decision 106 determines whether any user input was stored in 92 indicating that more input remains to be recognized. If so, the flow returns to step 82 to determine the field in which the stored text was entered and the flow proceeds for activating appropriate dictionaries and recognizing the text as described above. Conversely however, if no stored input remains to be recognized,decision 108 determines whether the user desires to edit any recognition errors in the recognized text such as by selecting aparticular icon 20 in FIG. 1. If so, errors may be corrected using any known technique, the present invention contemplates the editing method used not offer as alternative words the same words from other dictionaries as described above in conjunction with FIG. 6. - Once the recognized text is correct,
decision 112 determines whether the user desires to append an optional signature or other information to the recognized text as a measure of authentication. This alternate embodiment is particularly useful with the present invention in a medical application such as to authenticate a prescription from a medical doctor. If a signature is desired, it is appended instep 114 to the text or into a signature field. -
Decision 116 determines whether the optional wireless modem (17 in FIG. 2) is used in the application of the present invention such as to transmit a prescription to a pharmacy to be filled for a patient. If so, the information (with our without the signature) is transmitted instep 118 prior to returning to FIG. 7 to await further input from the user. - FIG. 10 illustrates an alternate preferred embodiment for optionally entering a personal signature or other symbol to be used as authentication information according to the present invention. An authentication or signature mode can be selected for example by the user selecting a
particular icon 20 in thetool bar 22 of FIG. 1. In this mode, a graphical image (window) 120 is presented to the user on thedisplay 4 of thecomputing device 2 of FIG. 1. Preferably, thegraphical image 120 includes asignature area 122 and may also include a command (tool bar)area 124 that includes several icons 126-130 used to affect editing or other functions and astatus area 132 used to convey information to the user. In the illustrated example, the signature “William Smith” has been handwritten in thesignature area 124 to be stored and later appended to other handwritten input or sent to other application programs (34-38 in FIG. 3) for the convenience of the user. According to the invention, the signature “ink” is not applied to the recognizer, but rather, is stored as information representing the “ink” to be used, for example, by a doctor to authenticate a drug prescription. - Accordingly, it will be appreciated by those skilled in the art that the present invention provides significant flexibility to handwriting recognition programs by activating selective sets of multiple specialized or general recognition dictionaries as described above. Several optional features of the present invention offer significant advantages for use in a wide variety of applications. Further optional variants of the present invention include the user of multiple windows (pages) that each may have one or more fields and having the active sets of dictionaries change depending upon which page (window) is being displayed to the user. Also, the recognition engine used to process the handwritten input with the active dictionaries may change depending upon the input field or window. In this regard, some fields may utilized a printed character handwriting recognizer while other field may employ a cursive handwriting recognition engine.
Claims (25)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/524,064 US6633672B1 (en) | 1995-12-28 | 2000-03-13 | Handwriting recognition method and apparatus having multiple selectable dictionaries |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US08/580,265 US6055333A (en) | 1995-12-28 | 1995-12-28 | Handwriting recognition method and apparatus having multiple selectable dictionaries |
US09/524,064 US6633672B1 (en) | 1995-12-28 | 2000-03-13 | Handwriting recognition method and apparatus having multiple selectable dictionaries |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US08/580,265 Continuation US6055333A (en) | 1995-12-28 | 1995-12-28 | Handwriting recognition method and apparatus having multiple selectable dictionaries |
Publications (2)
Publication Number | Publication Date |
---|---|
US6633672B1 US6633672B1 (en) | 2003-10-14 |
US20030194130A1 true US20030194130A1 (en) | 2003-10-16 |
Family
ID=24320396
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US08/580,265 Expired - Lifetime US6055333A (en) | 1995-12-28 | 1995-12-28 | Handwriting recognition method and apparatus having multiple selectable dictionaries |
US09/524,064 Expired - Lifetime US6633672B1 (en) | 1995-12-28 | 2000-03-13 | Handwriting recognition method and apparatus having multiple selectable dictionaries |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US08/580,265 Expired - Lifetime US6055333A (en) | 1995-12-28 | 1995-12-28 | Handwriting recognition method and apparatus having multiple selectable dictionaries |
Country Status (1)
Country | Link |
---|---|
US (2) | US6055333A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050039015A1 (en) * | 2001-08-17 | 2005-02-17 | Peter Ladanyl | Electronic writing device and method for generating an electronic signature |
US20110080608A1 (en) * | 2009-10-01 | 2011-04-07 | Samsung Electronics Co., Ltd. | Image forming apparatus and job performing method |
Families Citing this family (74)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8352400B2 (en) | 1991-12-23 | 2013-01-08 | Hoffberg Steven M | Adaptive pattern recognition based controller apparatus and method and human-factored interface therefore |
US6003007A (en) * | 1996-03-28 | 1999-12-14 | Dirienzo; Andrew L. | Attachment integrated claims system and operating method therefor |
ATE376696T1 (en) * | 1996-11-15 | 2007-11-15 | Toho Business Man Ct | BUSINESS MANAGEMENT SYSTEM |
FI981154A (en) * | 1998-05-25 | 1999-11-26 | Nokia Mobile Phones Ltd | Voice identification procedure and apparatus |
US7904187B2 (en) | 1999-02-01 | 2011-03-08 | Hoffberg Steven M | Internet appliance system and method |
US6816274B1 (en) * | 1999-05-25 | 2004-11-09 | Silverbrook Research Pty Ltd | Method and system for composition and delivery of electronic mail |
US20040260577A1 (en) * | 1999-11-15 | 2004-12-23 | Recare, Inc. | Electronic healthcare information and delivery management system with an integrated medical search architecture and capability |
US6766490B1 (en) * | 2000-03-03 | 2004-07-20 | Palmone, Inc. | Reduced table size forward error correcting encoder |
US6782974B2 (en) * | 2000-05-08 | 2004-08-31 | Richard Leifer | Server call system |
US6826551B1 (en) * | 2000-05-10 | 2004-11-30 | Advanced Digital Systems, Inc. | System, computer software program product, and method for producing a contextual electronic message from an input to a pen-enabled computing system |
US6724936B1 (en) | 2000-08-23 | 2004-04-20 | Art-Advanced Recognition Technologies, Ltd. | Handwriting input device and method using a single character set |
US6988088B1 (en) * | 2000-10-17 | 2006-01-17 | Recare, Inc. | Systems and methods for adaptive medical decision support |
US6816615B2 (en) * | 2000-11-10 | 2004-11-09 | Microsoft Corporation | Implicit page breaks for digitally represented handwriting |
US20050107672A1 (en) * | 2000-11-22 | 2005-05-19 | Recare, Inc. | System and method for external input of disease management algorithm |
US8301462B2 (en) * | 2000-11-22 | 2012-10-30 | Catalis, Inc. | Systems and methods for disease management algorithm integration |
CN1443329A (en) * | 2000-11-22 | 2003-09-17 | 里科尔公司 | System and methods for documenting medical findings of physical examination |
US20090125322A9 (en) * | 2000-11-22 | 2009-05-14 | Recare, Inc. | Integrated virtual consultant |
US20020107885A1 (en) * | 2001-02-01 | 2002-08-08 | Advanced Digital Systems, Inc. | System, computer program product, and method for capturing and processing form data |
AUPR399601A0 (en) * | 2001-03-27 | 2001-04-26 | Silverbrook Research Pty. Ltd. | An apparatus and method(ART108) |
CN1190721C (en) * | 2001-08-08 | 2005-02-23 | 国际商业机器公司 | Synergic hand-write input system and method |
US20030071850A1 (en) * | 2001-10-12 | 2003-04-17 | Microsoft Corporation | In-place adaptive handwriting input method and system |
US6986106B2 (en) | 2002-05-13 | 2006-01-10 | Microsoft Corporation | Correction widget |
US20030214553A1 (en) * | 2002-05-14 | 2003-11-20 | Microsoft Corporation | Ink regions in an overlay control |
US7925987B2 (en) * | 2002-05-14 | 2011-04-12 | Microsoft Corporation | Entry and editing of electronic ink |
US7137076B2 (en) * | 2002-07-30 | 2006-11-14 | Microsoft Corporation | Correcting recognition results associated with user input |
WO2004015543A2 (en) * | 2002-08-09 | 2004-02-19 | Recare, Inc. | Method and system for context-sensitive recognition of human input |
WO2004027673A1 (en) * | 2002-09-20 | 2004-04-01 | Siemens Dematic Postal Automation, L.P. | Hand held ocr apparatus and method |
US20040172306A1 (en) * | 2002-12-02 | 2004-09-02 | Recare, Inc. | Medical data entry interface |
AU2003298751A1 (en) * | 2002-12-03 | 2004-06-23 | Recare, Inc. | Data structures for context based rule application |
WO2004051428A2 (en) * | 2002-12-03 | 2004-06-17 | Recare, Inc. | Electronic prescription system |
US7295339B2 (en) * | 2003-03-19 | 2007-11-13 | Kabushiki Kaisha Toshiba | Image forming apparatus |
US20060277159A1 (en) * | 2003-08-15 | 2006-12-07 | Napper Jonathon L | Accuracy in searching digital ink |
US7848573B2 (en) * | 2003-12-03 | 2010-12-07 | Microsoft Corporation | Scaled text replacement of ink |
US7506271B2 (en) * | 2003-12-15 | 2009-03-17 | Microsoft Corporation | Multi-modal handwriting recognition correction |
US8442331B2 (en) | 2004-02-15 | 2013-05-14 | Google Inc. | Capturing text from rendered documents using supplemental information |
US7707039B2 (en) | 2004-02-15 | 2010-04-27 | Exbiblio B.V. | Automatic modification of web pages |
US20060041484A1 (en) * | 2004-04-01 | 2006-02-23 | King Martin T | Methods and systems for initiating application processes by data capture from rendered documents |
US20060136629A1 (en) * | 2004-08-18 | 2006-06-22 | King Martin T | Scanner having connected and unconnected operational behaviors |
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 |
US20080313172A1 (en) * | 2004-12-03 | 2008-12-18 | King Martin T | Determining actions involving captured information and electronic content associated with rendered documents |
US8146156B2 (en) | 2004-04-01 | 2012-03-27 | Google Inc. | Archive of text captures from rendered documents |
US20060081714A1 (en) | 2004-08-23 | 2006-04-20 | King Martin T | Portable scanning device |
US9116890B2 (en) | 2004-04-01 | 2015-08-25 | Google Inc. | 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 |
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 |
US7990556B2 (en) | 2004-12-03 | 2011-08-02 | Google Inc. | Association of a portable scanner with input/output and storage devices |
US8621349B2 (en) | 2004-04-01 | 2013-12-31 | Google Inc. | Publishing techniques for adding value to a rendered document |
US8793162B2 (en) * | 2004-04-01 | 2014-07-29 | Google Inc. | Adding information or functionality to a rendered document via association with an electronic counterpart |
US9143638B2 (en) | 2004-04-01 | 2015-09-22 | Google Inc. | Data capture from rendered documents using handheld device |
CN100407223C (en) * | 2004-04-02 | 2008-07-30 | 诺基亚公司 | Apparatus and method for handwriting recognition |
US7580029B2 (en) * | 2004-04-02 | 2009-08-25 | Nokia Corporation | Apparatus and method for handwriting recognition |
US8713418B2 (en) | 2004-04-12 | 2014-04-29 | Google Inc. | Adding value to a rendered document |
US8620083B2 (en) | 2004-12-03 | 2013-12-31 | Google Inc. | Method and system for character recognition |
US8489624B2 (en) | 2004-05-17 | 2013-07-16 | Google, Inc. | Processing techniques for text capture from a rendered document |
US9460346B2 (en) | 2004-04-19 | 2016-10-04 | Google Inc. | Handheld device for capturing text from both a document printed on paper and a document displayed on a dynamic display device |
US8874504B2 (en) | 2004-12-03 | 2014-10-28 | Google Inc. | Processing techniques for visual capture data from a rendered document |
US20050273363A1 (en) * | 2004-06-02 | 2005-12-08 | Catalis, Inc. | System and method for management of medical and encounter data |
WO2005122042A2 (en) * | 2004-06-02 | 2005-12-22 | Catalis, Inc. | Method and system for generating medical narrative |
US8346620B2 (en) | 2004-07-19 | 2013-01-01 | Google Inc. | Automatic modification of web pages |
US20060029273A1 (en) * | 2004-08-03 | 2006-02-09 | Catalis, Inc. | Physician communication system |
US20060031097A1 (en) * | 2004-08-09 | 2006-02-09 | Catalis, Inc. | Practice management system |
JP4681870B2 (en) * | 2004-12-17 | 2011-05-11 | キヤノン株式会社 | Image processing apparatus, image processing method, and computer program |
US7639876B2 (en) * | 2005-01-14 | 2009-12-29 | Advanced Digital Systems, Inc. | System and method for associating handwritten information with one or more objects |
US7720286B2 (en) * | 2005-05-25 | 2010-05-18 | Advanced Digital Systems, Inc. | System and method for associating handwritten information with one or more objects via discontinuous regions of a printed pattern |
US7899251B2 (en) * | 2006-06-05 | 2011-03-01 | Microsoft Corporation | Balancing out-of-dictionary and in-dictionary recognition scores |
EP2067119A2 (en) | 2006-09-08 | 2009-06-10 | Exbiblio B.V. | Optical scanners, such as hand-held optical scanners |
WO2010096193A2 (en) | 2009-02-18 | 2010-08-26 | Exbiblio B.V. | Identifying a document by performing spectral analysis on the contents of the document |
EP2406767A4 (en) | 2009-03-12 | 2016-03-16 | Google Inc | Automatically providing content associated with captured information, such as information captured 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 |
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 |
CN102455867B (en) * | 2011-09-29 | 2015-06-24 | 北京壹人壹本信息科技有限公司 | Method and device for matching handwritten character information |
US9659213B2 (en) | 2015-07-03 | 2017-05-23 | Cognizant Technology Solutions India Pvt. Ltd. | System and method for efficient recognition of handwritten characters in documents |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4531231A (en) * | 1983-01-19 | 1985-07-23 | Communication Intelligence Corporation | Method for distinguishing between complex character sets |
US4573196A (en) * | 1983-01-19 | 1986-02-25 | Communications Intelligence Corporation | Confusion grouping of strokes in pattern recognition method and system |
US5265174A (en) * | 1989-03-03 | 1993-11-23 | Canon Kabushiki Kaisha | Pattern recognition apparatus |
JPH0381817A (en) * | 1989-08-25 | 1991-04-08 | Hitachi Ltd | Hand-written input information processor and hand-written input information system using the processor |
US5031223A (en) * | 1989-10-24 | 1991-07-09 | International Business Machines Corporation | System and method for deferred processing of OCR scanned mail |
US5361310A (en) * | 1990-01-19 | 1994-11-01 | Fujitsu Limited | Handwriting entry processing system using keyboard and mouse interfaces requiring no modification of an application program |
US5267327A (en) * | 1990-03-30 | 1993-11-30 | Sony Corporation | Apparatus and method for registering the handwriting of a user so it can be translated into block characters |
US5497319A (en) * | 1990-12-31 | 1996-03-05 | Trans-Link International Corp. | Machine translation and telecommunications system |
US5428805A (en) * | 1992-12-22 | 1995-06-27 | Morgan; Michael W. | Method and apparatus for recognizing and performing handwritten calculations |
US5734749A (en) * | 1993-12-27 | 1998-03-31 | Nec Corporation | Character string input system for completing an input character string with an incomplete input indicative sign |
US5754671A (en) * | 1995-04-12 | 1998-05-19 | Lockheed Martin Corporation | Method for improving cursive address recognition in mail pieces using adaptive data base management |
US5963666A (en) * | 1995-08-18 | 1999-10-05 | International Business Machines Corporation | Confusion matrix mediated word prediction |
-
1995
- 1995-12-28 US US08/580,265 patent/US6055333A/en not_active Expired - Lifetime
-
2000
- 2000-03-13 US US09/524,064 patent/US6633672B1/en not_active Expired - Lifetime
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050039015A1 (en) * | 2001-08-17 | 2005-02-17 | Peter Ladanyl | Electronic writing device and method for generating an electronic signature |
US20110080608A1 (en) * | 2009-10-01 | 2011-04-07 | Samsung Electronics Co., Ltd. | Image forming apparatus and job performing method |
US8405856B2 (en) * | 2009-10-01 | 2013-03-26 | Samsung Electronics Co., Ltd. | Image forming apparatus and job performing method |
Also Published As
Publication number | Publication date |
---|---|
US6633672B1 (en) | 2003-10-14 |
US6055333A (en) | 2000-04-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6633672B1 (en) | Handwriting recognition method and apparatus having multiple selectable dictionaries | |
US5956423A (en) | Method and system for data entry of handwritten symbols | |
US7505627B2 (en) | Apparatus and method for letter recognition | |
US7137076B2 (en) | Correcting recognition results associated with user input | |
US6690364B1 (en) | Method and system for on screen text correction via pen interface | |
US20050135678A1 (en) | Scaled text replacement of ink | |
JP3829366B2 (en) | Input device and input method | |
US20030099398A1 (en) | Character recognition apparatus and character recognition method | |
US7562314B2 (en) | Data processing apparatus and method | |
US20050052431A1 (en) | Apparatus and method for character recognition | |
US5787455A (en) | Method and apparatus for storing corrected words with previous user-corrected recognition results to improve recognition | |
US5917942A (en) | Device and method for handwriting recognition with adaptive weighting of recognition data | |
KR100506231B1 (en) | Apparatus and method for inputting character in terminal having touch screen | |
US20020085772A1 (en) | Intelligent correction key | |
JPH04290184A (en) | Handwritten document creation device | |
JPH0950433A (en) | Handwritten character recognition device | |
JP3091543B2 (en) | Document processing device | |
JPH08147096A (en) | Handwriting input method and device | |
JP2714230B2 (en) | Handwriting calculation processor | |
JP3153704B2 (en) | Character recognition device | |
JP3184662B2 (en) | Document creation device and kanji conversion method | |
JPH10320107A (en) | Handwritten character input device having handwritten character recognizing function | |
JPH067309B2 (en) | Electronics | |
JP2598894B2 (en) | Handwritten character recognition device | |
JPH11184970A (en) | Handwritten data input device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: MOTOROLA, INC., ILLINOIS Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:GUZIK, KENNETH;HUFF, ALAN;NAG, RONJON;REEL/FRAME:010820/0945 Effective date: 19960417 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
FPAY | Fee payment |
Year of fee payment: 4 |
|
AS | Assignment |
Owner name: MOTOROLA MOBILITY, INC, ILLINOIS Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MOTOROLA, INC;REEL/FRAME:025673/0558 Effective date: 20100731 |
|
FPAY | Fee payment |
Year of fee payment: 8 |
|
AS | Assignment |
Owner name: MOTOROLA MOBILITY LLC, ILLINOIS Free format text: CHANGE OF NAME;ASSIGNOR:MOTOROLA MOBILITY, INC.;REEL/FRAME:029216/0282 Effective date: 20120622 |
|
AS | Assignment |
Owner name: GOOGLE TECHNOLOGY HOLDINGS LLC, CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MOTOROLA MOBILITY LLC;REEL/FRAME:034293/0138 Effective date: 20141028 |
|
FPAY | Fee payment |
Year of fee payment: 12 |