Apparatus and method for handwriting recognition

• US 20050249419A1
• Filed: 05/04/2004
• Published: 11/10/2005
• Est. Priority Date: 05/04/2004
• Status: Active Grant

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Rieman, John
• Granted Patent: US 8,411,958 B2
• Time in Patent Office: Days
• US Class Current: 382/229
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/2272 with lexical matching
• CPC Class Codes: G06V 30/2276 with probabilistic networks, e.g. hidden Markov models
• CPC Class Codes: G06V 30/268 Lexical context

Abstract

A method and device is provided for recognizing characters in a handwritten input representing an input character string. A character sub-string preceding an unrecognized character in the input character string is determined. Handwriting recognition is used to provide one or more candidate characters for the unrecognized character. One of the one or more candidate characters is then selected. The candidate character selected, is the one which is most likely to be a correct recognition of the unrecognized character based on the determined character sub-string.

Claims

1. A method for recognizing characters in a handwritten input representing an input character string, comprising:

determining a character sub-string preceding an unrecognized character in the input character string;

providing, by means of handwriting recognition, one or more candidate characters for the unrecognized character; and

selecting, based on the determined character sub-string, one of the one or more candidate characters which is most likely to be a correct recognition of the unrecognized character.

2. The method of claim 1, wherein the candidate character is selected which has the highest probability to succeed the character sub-string.

3. The method of claim 1, further comprising:

identifying, amongst stored character strings, one or more candidate character strings comprising an initial character sub-string identical to the determined character sub-string,

wherein the selecting is based on the one or more candidate character strings.

4. The method of claim 3, wherein the selecting is based on a next character succeeding the initial character sub-string of each of the one or more candidate character strings.

5. The method of claim 1, wherein the determining of a character sub-string comprises:

the determining of a character sub-string consisting of all characters of the input character string preceding the unrecognized character.

6. The method of claim 1, wherein the determining of a character sub-string comprises:

determining a character sub-string consisting of a terminal character sub-string of the input character string preceding the unrecognized character.

7. The method of claim 1, wherein the determining of a character sub-string comprises:

identifying space characters in the input character string; and

determining a character sub-string consisting of a terminal character sub-string of the input character string preceding the unrecognized character and succeeding an identified space character.

8. The method of claim 7, wherein a character sub-string is determined consisting of a terminal character sub-string of the input character string preceding the unrecognized character and succeeding an identified last space character before the unrecognized character.

9. The method of claim 3, wherein the determining of a character sub-string comprises:

identifying any initial character sub-string of the input character string preceding the unrecognized character, which is identical to one of the stored character strings or to an initial character sub-string of one or more of the stored character strings, and which together with a succeeding character is not identical to any one of the stored character strings or to an initial character sub-string of any one of the stored character strings; and

determining a character sub-string consisting of a terminal character sub-string of the input character string preceding the unrecognized character and succeeding any identified initial character sub-string.

10. The method of claim 3, wherein the determining of a character sub-string comprises:

identifying space characters in the input character string;

identifying any word initial character sub-string of the input character string preceding the unrecognized character and succeeding an identified last space character before the unrecognized character, which is identical to one of the stored character strings or to an initial character sub-string of one or more of the stored character strings, and which together with a succeeding character is not identical to any one of the stored character strings or to an initial character sub-string of any one of the stored character strings; and

determining a character sub-string consisting of a terminal character sub-string of the input character string preceding the unrecognized character and succeeding any identified word initial character sub-string.

11. The method of claim 3, wherein the stored character strings are chosen from the following type of character strings:

phrases, words, word stubs and frequently used character sequences.

12. The method of claim 1, further comprising:

for each character in sequence of the input character string preceding the unrecognized character;

providing, by means of handwriting recognition, one or more candidate characters for the character; and

selecting, based on the characters preceding the character in the input character string, one of the one or more candidate characters which is most likely to be a correct recognition of the character.

13. A device for recognizing characters in a handwritten input representing an input character string, comprising:

a processor arranged to;

determine a character sub-string preceding an unrecognized character in the input character string,

provide, by means of handwriting recognition, one or more candidate characters for the unrecognized character, and

select, based on the determined character sub-string, one of the one or more candidate characters which is most likely to be a correct recognition of the unrecognized character.

14. The device of claim 13, wherein processor is arranged to select the candidate character is which has the highest probability to succeed the character sub-string.

15. The device of claim 13, further comprising

a memory for storing character strings, and

wherein the processor is further arranged to:

identify, amongst the stored character strings, one or more candidate character strings comprising an initial character sub-string identical to the determined character sub-string, and

select, based on the one or more candidate character strings, one of the one or more candidate characters which is most likely to be a correct recognition of the unrecognized character.

16. The device of claim 15, wherein the processor is arranged to select, based on a next character succeeding the initial character sub-string of each of the one or more candidate character strings, one of the one or more candidate characters which is most likely to be a correct recognition of the unrecognized character.

17. The device of claim 13, wherein the processor is further arranged to:

identify space characters in the input character string, and

determine a character sub-string consisting of a terminal character sub-string of the input character string preceding the unrecognized character and succeeding an identified last space character before the unrecognized character.

18. The device of claim 13, wherein the stored character strings are chosen from the following type of character strings:

phrases, words, word stubs and frequently used character sequences.

19. The device of claim 13, wherein the device is a mobile terminal.

20. A method for recognizing characters in a handwritten input representing an input character string, comprising:

determining a character sub-string preceding an unrecognized character in the input character string;

identifying, amongst the stored character strings, one or more candidate character strings comprising an initial character sub-string identical to the determined character sub-string,

providing, by means of handwriting recognition, one or more candidate characters for the unrecognized character, and

selecting, based on a next character succeeding the initial character sub-string of each of the one or more candidate character strings, one of the one or more candidate characters which is most likely to be a correct recognition of the unrecognized character.

21. The method of claim 20, wherein the determining of a character sub-string comprises:

identifying space characters in the input character string; and

determining a character sub-string consisting of a terminal character sub-string of the input character string preceding the unrecognized character and succeeding an identified last space character before the unrecognized character.

22. The method of claim 20, wherein the determining of a character sub-string comprises:

identifying space characters in the input character string;

identifying any word initial character sub-string of the input character string preceding the unrecognized character and succeeding an identified last space character before the unrecognized character, which is identical to one of the stored character strings or to an initial character sub-string of one or more of the stored character strings, and which together with a succeeding character is not identical to any one of the stored character strings or to an initial character sub-string of any one of the stored character strings; and

determining a character sub-string consisting of a terminal character sub-string of the input character string preceding the unrecognized character and succeeding any identified word initial character sub-string.

23. A mobile terminal comprising:

an interface for retrieving handwritten input representing an input character string;

a memory for storing frequently occuring character strings;

a processor arranged to;

determine a character sub-string preceding an unrecognized character in the input character string;

identify, amongst the stored character strings, one or more candidate character strings comprising an initial character sub-string identical to the determined character sub-string,

to provide, by means of handwriting recognition, one or more candidate characters for the unrecognized character, and

to select, based on a next character succeeding the initial character sub-string of each of the one or more candidate character strings, one of the one or more candidate characters which is most likely to be a correct recognition of the unrecognized character.

24. The mobile terminal of claim 23, wherein the processor is further arranged to:

identify space characters in the input character string, and to determine a character sub-string consisting of a terminal character sub-string of the input character string preceding the unrecognized character and succeeding an identified last space character before the unrecognized character.

25. The mobile terminal of claim 23, wherein the processor is arranged to determine a character sub-string by:

identifying space characters in the input character string;

identifying any word initial character sub-string of the input character string preceding the unrecognized character and succeeding an identified last space character before the unrecognized character, which is identical to one of the stored character strings or to an initial character sub-string of one or more of the stored character strings, and which together with a succeeding character is not identical to any one of the stored character strings or to an initial character sub-string of any one of the stored character strings; and

determining a character sub-string consisting of a terminal character sub-string of the input character string preceding the unrecognized character and succeeding any identified word initial character sub-string.