Combined dictionary based and likely character string method of handwriting recognition

• US 6,005,973 A
• Filed: 07/22/1997
• Issued: 12/21/1999
• Est. Priority Date: 12/01/1993
• Status: Expired due to Term

• Current Assignee: Google Technology Holdings LLC (Alphabet Inc.)
• Original Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Inventors: Kortge, Chris A., Seybold, John L. C.
• Primary Examiner(s): COUSO, YON JUNG
• Application Number:
  US08/898,633
• Time in Patent Office: 882 Days
• Field of Search: 382/188, 382/189, 382/187, 382/229, 382/230, 382/186
• US Class Current: 382/187
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/127 with the intervention of an operator
• CPC Class Codes: G06V 30/1423 the instrument generating sequences of position coordinates corresponding to handwriting preprocessing or recognising digital ink G06V30/32
• CPC Class Codes: G06V 30/2272 with lexical matching
• CPC Class Codes: G06V 30/268 Lexical context
• CPC Class Codes: G06V 30/32 Digital ink
• CPC Class Codes: G06V 30/387 using human interaction, e.g. selection of the best displayed recognition candidate

Abstract

In a handwriting recognition process, a list of candidate recognized words is identified (202) as a function of both comparison of dictionary entries to various combinations of recognized character combinations, and through a most likely character string and most likely string of digits analysis as developed without reference to the dictionary. The process selects (301) a word from the list and presents (302) this word to the user. The user then has the option of displaying (303) this list. When displaying the list, candidate words developed with reference to the dictionary are displayed in segregated manner from the most likely character string words and the most likely string of digits. The user can charge the selected word by choosing from the list, or edit the selected word. When the user selects the most likely character string as the correct representation of the handwritten input to be recognized, the process automatically updates (310) the dictionary to include the most likely character string The same process can occur when the user selects the most likely string of digits.

Claims

1. A method comprising the steps of:

analyzing handwritten input to provide one or more candidate characters;

comparing at least some entries in a dictionary with at least some combinations of the candidate characters to identify at least one candidate dictionary word that might represent the handwritten input;

determining at least one likely non-dictionary character string from at least some combinations of the candidate characters that has a highest likelihood of representing the handwritten input, the determining step being independent of the comparing step;

identifying a likely string of digits of a numerical or punctuational value; and

identifying for presentation in a list of alternate word selections;

the at least one candidate dictionary word;

the at least one likely non-dictionary character string when the likely character string is not one of the candidate words otherwise so provided in the list; and

the likely string of digits.

2. The method of claim 1, wherein the step of analyzing handwritten input to provide a plurality of candidate characters includes the step of determining a likelihood of being correct for at least some of the plurality of candidate characters.

3. The method of claim 1, wherein the step of comparing at least some entries in the dictionary with at least some combinations of candidate characters to identify candidate dictionary words that might represent the input includes the step of comparing all entries in the dictionary with at least some combinations of candidate characters to identify candidate words that might represent the input.

4. The method of claim 3, wherein the step of comparing all entries in the dictionary with at least some combinations of candidate characters includes the step of comparing at least part of each entry with at least part of each combination of candidate characters.

5. The method of claim 1, where in the step of identifying as a likely non-dictionary character string a combination of candidate characters that has a highest combined corresponding likelihood of being correct includes the step of determining a likelihood of accuracy for individual candidate characters.

6. The method of claim 5, wherein the step of identifying as a likely non-dictionary character string a combination of candidate characters that has a highest combined corresponding likelihood of being correct also includes the step of determining which combinations of individual candidate characters has a highest probability of being accurate as determined using character N-gram statistics.

7. The method of claim 1, and further including the step of using the list to provide one selected word.

8. The method of claim 1, and further including the step of displaying the list.

9. A method comprising the steps of:

analyzing handwritten input to provide one or more candidate characters;

comparing at least some entries in a dictionary with at least some combinations of the candidate characters to identify at least one candidate dictionary word that might represent the handwritten input;

determining at least one likely non-dictionary string from at least some combinations of the candidate characters that has a highest likelihood of representing the handwritten input, the determining step being independent of the comparing step;

identifying for presentation a list including;

the at least one candidate dictionary word; and

the likely non-dictionary string when the likely non-dictionary string is not one of the candidate dictionary word otherwise so provided in the list; and

selecting one of the words in the list to provide a selected word.

10. The method of claim 9, and further including the steps of:

receiving input from the user indicating a request to display at least part of the list;

displaying the at least one candidate dictionary word and the likely non-dictionary character string when the likely non-dictionary character string is not one of the candidate dictionary words otherwise so provided in the list.

11. The method of claim 10, and further including the step of:

receiving input from the user indicating a selection of the likely non-dictionary character string;

automatically updating the dictionary to include the likely non-dictionary character string.

12. The method of claim 9, wherein the step of analyzing the handwritten input to provide one or more candidate characters includes the step of determining a likelihood of being correct for at least some of the plurality of candidate characters.

13. The method of claim 9, wherein the step of comparing at least some entries in the dictionary with at least some combinations of candidate characters to identify candidate dictionary words that might represent the input includes the step of comparing all entries in the dictionary with at least some combinations of candidate characters to identify candidate dictionary words that might represent the input.

14. The method of claim 13, wherein the step of comparing all entries in the dictionary with at least some combinations of candidate characters includes the step of comparing at least part of each entry with at least part of each combination of candidate characters.

15. The method of claim 9, where in the step of identifying as a likely non-dictionary character string a combination of candidate characters that has a highest combined corresponding likelihood of being correct includes the step of determining a likelihood of accuracy for individual candidate characters.

16. The method of claim 15, wherein the step of identifying as a likely non-dictionary character string a combination of candidate characters that has a highest combined corresponding likelihood of being correct also includes the step of determining which combinations of individual candidate characters has a highest probability of being accurate as determined using character N-gram statistics.

17. A method comprising the steps of:

analyzing handwritten alphanumeric input comprising a word that includes a plurality of alphanumeric characters to provide a plurality of candidate characters that may correspond to the alphanumeric characters that comprise the word;

automatically accessing a dictionary and comparing at least some word entries in the dictionary with at least some combinations of the candidate characters to identify candidate dictionary words that might represent the word;

automatically identifying as a likely non-dictionary string a combination of candidate characters that has a highest combined corresponding likelihood of being correct without regard to the dictionary;

providing a list of words including (i) at least one of the candidate dictionary words and (ii) the likely non-dictionary string when the likely string is not one of the candidate words otherwise so provided in the list;

selecting one of the words in the list to provide a selected word;

displaying the selected word;

displaying upon a request to display at least part of the list; and

displaying at least one of the candidate dictionary words and the likely non-dictionary string when the likely non-dictionary string is not one of the candidate words otherwise so provided in the list.

18. The method of claim 17, where in the step of identifying as a likely non-dictionary character string a combination of candidate characters that has a highest combined corresponding likelihood of being correct includes the step of determining a likelihood of accuracy for individual candidate characters.

19. A device capable of recognizing and editing handwritten input, comprising:

a touch-sensitive display for receiving handwritten input; and

digital processing circuitry programmed to;

analyze the handwritten input to provide one or more candidate characters;

compare at least some entries in a dictionary with at least some combinations of the candidate characters to identify at least one candidate dictionary word that might represent the handwritten input;

determine at least one likely non-dictionary character string from at least some combination of the candidate characters that has a highest likelihood of representing the handwritten input, wherein the process of determining is independent of the process of comparing; and

identify for presentation in a list of alternate word selections including;

the at least one candidate dictionary word; and

the at least one likely non-dictionary character string when the likely character string is not one of the candidate words otherwise so provided in the list.