Recognizing handwritten words

• US 8,175,389 B2
• Filed: 03/30/2009
• Issued: 05/08/2012
• Est. Priority Date: 03/30/2009
• Status: Active Grant

• Current Assignee: Synaptics Incorporated
• Original Assignee: Synaptics Incorporated
• Inventors: Matic, Nada P., Cheng, Yi-Hsun E.
• Primary Examiner(s): STREGE, JOHN B
• Application Number:
  US12/413,875
• Publication Number:
  US 20100246964A1
• Time in Patent Office: 1,135 Days
• Field of Search: 382/185, 382/186, 382/187
• US Class Current: 382/187
• CPC Class Codes: G06V 30/2268 using stroke segmentation
• CPC Class Codes: G06V 30/36 Matching; Classification

Abstract

Recognizing handwritten words at an electronic device. A plurality of strokes is received at a common input region of an electronic device. The plurality of strokes in combination defines a word comprising a plurality of symbols, a relative geometry of a first subset of the plurality of strokes defines a first symbol and a relative geometry of a second subset of the plurality of strokes defines a second symbol such that the relative geometry of the first subset of the plurality of strokes is not related to the relative geometry of the second subset of the plurality of strokes, and at least one stroke of the first subset of the plurality of strokes is spatially superimposed over at least one stroke of the second subset of the plurality of strokes. The word is determined using a processor of the electronic device based on the plurality of strokes without requiring recognition of the plurality of symbols, wherein a word is determined based at least in part on an entry sequence of subsets of the plurality of strokes.

Claims

1. A computer-implemented method for recognizing handwritten words at an electronic device, said method comprising:

receiving a plurality of strokes at a common input region of said electronic device, wherein said plurality of strokes in combination defines a word comprising a plurality of symbols, wherein a relative geometry of a first subset of said plurality of strokes defines a first symbol and a relative geometry of a second subset of said plurality of strokes defines a second symbol such that said relative geometry of said first subset of said plurality of strokes is not related to said relative geometry of said second subset of said plurality of strokes, and wherein at least one stroke of said first subset of said plurality of strokes is spatially superimposed over at least one stroke of said second subset of said plurality of strokes; and

determining said word using a processor of said electronic device based on said plurality of strokes without requiring recognition of said plurality of symbols, wherein a word is determined based at least in part on an entry sequence of subsets of said plurality of strokes.

2. The computer-implemented method of claim 1 wherein said determining said word based on said plurality of strokes comprises:

inputting said plurality of strokes into a statistical classifier trained to identify said word; and

indexing an output of said statistical classifier to a dictionary determining said word.

3. The computer-implemented method of claim 1 wherein a relative geometry of a stroke comprises a relative position and a proportional size of said stroke relative to other strokes of a symbol.

4. The computer-implemented method of claim 1 wherein said relative position comprises a relative horizontal position and a relative vertical position of said stroke relative to said other strokes of said symbol.

5. The computer-implemented method of claim 2 wherein said wherein said dictionary is selected from a list consisting essentially of Pinyin representations of words, Bopomofo representations of words, and Korean representations of words.

6. The computer-implemented method of claim 2 wherein said dictionary comprises a predetermined limited set of words.

7. The computer-implemented method of claim 2 wherein said dictionary comprises an application-specific dictionary.

8. The computer-implemented method of claim 2 wherein said dictionary comprises phonetic representations of an ideographic language.

9. The computer-implemented method of claim 1 wherein a symbol is defined independent of an entry sequence of said plurality of strokes.

10. A non-transitory computer-readable medium having instructions encoded thereon for enabling a processor to perform a method for recognizing handwritten symbols, said method comprising:

receiving a plurality of strokes at a common input region of an electronic device, wherein said plurality of strokes in combination defines a word comprising a plurality of symbols, wherein a relative geometry of a first subset of said plurality of strokes defines a first symbol and a relative geometry of a second subset of said plurality of strokes defines a second symbol such that said relative geometry of said first subset of said plurality of strokes is not related to said relative geometry of said second subset of said plurality of strokes, and wherein at least one stroke of said first subset of said plurality of strokes is spatially superimposed over at least one stroke of said second subset of said plurality of strokes; and

determining said word based on said plurality of strokes without requiring recognition of said plurality of symbols, wherein a word is determined based at least in part on an entry sequence of subsets of said plurality of strokes.

11. The computer-readable medium of claim 10 wherein said determining said plurality of word based on said plurality of strokes comprises:

inputting said plurality of strokes into a statistical classifier trained to identify said word; and

indexing an output of said statistical classifier to a dictionary determining said word.

12. The computer-readable medium of claim 10 wherein a relative geometry of a stroke comprises a relative position and a proportional size of said stroke relative to other strokes of a symbol.

13. The computer-readable medium of claim 12 wherein said relative position comprises a relative horizontal position and a relative vertical position of said stroke relative to said other strokes of said symbol.

14. The computer-readable medium of claim 11 wherein said dictionary is selected from a list consisting essentially of Pinyin representations of words, Bopomofo representations of words, and Korean representations of words.

15. The computer-readable medium of claim 11 wherein said dictionary comprises phonetic representations of an ideographic language.

16. The computer-readable medium of claim 11 wherein said dictionary comprises a predetermined limited set of words.

17. The computer-readable medium of claim 11 wherein said dictionary comprises an application-specific dictionary.

18. An electronic device comprising:

a processor;

a memory communicatively coupled to said processor; and

a common input region communicatively coupled to said processor and for receiving a plurality of strokes, wherein said plurality of strokes in combination define a symbol comprising a plurality of subset characters, wherein a relative geometry of a first subset of said plurality of strokes defines a first symbol and a relative geometry of a second subset of said plurality of strokes defines a second symbol such that said relative geometry of said first subset of said plurality of strokes is not related to said relative geometry of said second subset of said plurality of strokes, and wherein at least one stroke of said first subset of said plurality of strokes is spatially superimposed over at least one stroke of said second subset of said plurality of strokes;

wherein said processor is configured to determine said word based on said plurality of strokes without requiring recognition of said plurality of symbols, is configured to input said plurality of strokes into a statistical classifier trained to identify said word, and configured to index an output of said statistical classifier to a dictionary determining said word, wherein a word is determined based at least in part on an entry sequence of subsets of said plurality of strokes.

19. The electronic device of claim 18 wherein a relative geometry of a stroke comprises a relative position and a proportional size of said stroke relative to other strokes of a symbol.

20. The electronic device of claim 19 wherein said relative position comprises a relative horizontal position and a relative vertical position of said stroke relative to said other strokes of said symbol.

21. The electronic device of claim 18 wherein said dictionary is selected from a list consisting essentially of Pinyin representations of words, Bopomofo representations of words, Korean representations of words, and phonetic representations of an ideographic language.

22. The electronic device of claim 18 wherein said dictionary comprises a predetermined limited set of words.

23. The electronic device of claim 18 wherein said dictionary comprises an application-specific dictionary.