Method and apparatus for recognizing handwritten chinese characters

• US 20020168107A1
• Filed: 03/14/2002
• Published: 11/14/2002
• Est. Priority Date: 04/16/1998
• Status: Active Grant

• Current Assignee: Lenovo PC International Limited (Lenovo Group Ltd.)
• Original Assignee: International Business Machines Corporation
• Inventors: Su, Hui, Wang, Qian Ying, Tang, Donald T.
• Granted Patent: US 6,795,579 B2
• Time in Patent Office: Days
• US Class Current: 382/187
• CPC Class Codes: G06V 30/373 using a special pattern or subpattern alphabet

Abstract

A method for recognizing handwritten Chinese characters based on stroke recognition comprises steps of: recognizing handwritten strokes, updating stroke code sequences; retrieving in dictionaries/lexicons at least one corresponding character/phrase entry so as to obtain at least one candidate Chinese character/phrase; dynamically displaying the at least one candidate Chinese character/phrase; jumping to the step of recognizing strokes if it is judged that a next stroke is being written; inputting a displayed Chinese character/phrase into computers as the result of recognition if this character/phase is selected by the user.

Claims

1. A method of recognizing handwritten characters, the method comprising the steps of:

recognizing a current handwritten stroke intended to be associated with at least one character such that at least one stroke code is associated with a recognized stroke to form a current stroke code sequence, the current stroke code sequence including the current stroke code and previously formed related stroke codes, if such related stroke codes were previously formed;

retrieving from a source of characters one or more entries for display which correspond to the current stroke code sequence, the one or more entries representing one or more candidate characters;

displaying the one or more entries retrieved from the source of characters at the completion of each stroke;

repeating the recognition and retrieval steps if a next stroke is received such that the current stroke code sequence is formed from the stroke code associated with this stroke and stroke codes associated with preceding strokes; and

generating a recognition result associated with the one or more candidate characters if one or more candidate characters are selected as the intended at least one character.

2. The method of claim 1, wherein the source of characters is at least one dictionary.

3. The method of claim 1, wherein the at least one character includes a set of characters wherein the recognition, retrieval, and generating steps result in identification of one or more candidate sets of characters.

4. The method of claim 3, wherein the source of characters is at least one lexicon.

5. The method of claim 1, further including the step of recognizing a phonetic tag associated with the at least one intended character such that a range within the source of characters is specified and the retrieval step is performed within the range.

6. The method of claim 5, wherein the phonetic tag recognition step is performed prior to the stroke recognition step.

7. The method of claim 5, wherein the phonetic tag corresponds to a first alphabet in a complete phonetic representation of the character.

8. The method of claim 1, wherein the generating step is automatic when the retrieval step results in the identification of one of a single candidate character and a single candidate set of characters.

9. The method of claim 1, wherein the retrieving step includes retrieving each entry in the character source that contains a relevant stroke code sequence which corresponds to the current stroke code sequence.

10. The method of claim 1, wherein the retrieving step includes retrieving each entry in the character source that contains a relevant stroke code sequence which contains the same categories of stroke codes occurring the same amount of times as the current stroke code sequence.

11. The method of claim 1, wherein the retrieving step includes retrieving each entry in the character source that contains a relevant stroke code sequence resulting in a sum of differences between a number of times that respective categories of various stroke codes occur with respect to the relevant stroke code sequence and the current stroke code sequence is at least less than a predetermined threshold.

12. The method of claim 1, further including the step of modifying the source by changing a corresponding stroke code sequence associated with an entry based on the formed stroke code sequence and selection of the one or more candidate characters.

13. The method of claim 1, further comprising the step of modifying the source by adding a new entry containing the formed stroke code sequence to the source based on selection of the one or more candidate characters.

14. The method of claim 1, wherein the recognizing step further includes:

identifying one of the handwritten strokes and phonetic tags with handwritten strokes recognizable to a portable electronic device;

converting the handwritten strokes recognizable to the portable electronic device into one or more stroke codes; and

forming the current stroke code sequence from the one or more stroke codes.

16. The apparatus of claim 15, wherein the source of characters is at least one dictionary.

17. The apparatus of claim 15, wherein the at least one character includes a set of characters wherein the recognition, retrieval, and generation operations result in identification of one or more candidate sets of characters.

18. The apparatus of claim 17, wherein the source of characters is at least one lexicon.

19. The apparatus of claim 15, wherein the at least one processor is further operable to recognize a phonetic tag associated with the at least one intended character such that a range within the source of characters is specified and the retrieval operation is performed within the range.

20. The apparatus of claim 19, wherein the phonetic tag recognition operation is performed prior to the stroke recognition operation.

21. The apparatus of claim 19, wherein the phonetic tag corresponds to a first alphabet in a complete phonetic representation of the character.

22. The apparatus of claim 15, wherein the generation operation is automatic when the retrieval operation results in the identification of one of a single candidate character and a single candidate set of characters.

23. The apparatus of claim 15, wherein the retrieval operation includes retrieving each entry in the character source that contains a relevant stroke code sequence which corresponds to the current stroke code sequence.

24. The apparatus of claim 15, wherein the retrieval operation includes retrieving each entry in the character source that contains a relevant stroke code sequence which contains the same categories of stroke codes occurring the same amount of times as the current stroke code sequence.

25. The apparatus of claim 15, wherein the retrieval operation includes retrieving each entry in the character source that contains a relevant stroke code sequence resulting in a sum of differences between a number of times that respective categories of various stroke codes occur with respect to the relevant stroke code sequence and the current stroke code sequence is at least less than a predetermined threshold.

26. The apparatus of claim 15, wherein the processor is further operable to modify the source by changing a corresponding stroke code sequence associated with an entry based on the formed stroke code sequence and selection of the one or more candidate characters.

27. The apparatus of claim 15, wherein the processor is further operable to modify the source by adding a new entry containing the formed stroke code sequence to the source based on selection of the one or more candidate characters.

28. The apparatus of claim 15, wherein the recognition operation further includes identifying one of the handwritten strokes and phonetic tags with handwritten strokes recognizable to a portable electronic device, converting the handwritten strokes recognizable to the portable electronic device into one or more stroke codes, and forming the current stroke code sequence from the one or more stroke codes.

30. The method of claim 1, wherein the character is a Chinese character.

31. The apparatus of claim 15, wherein the character is a Chinese character.

32. The article of manufacture of claim 29, wherein the character is a Chinese character.

15. Apparatus for recognizing handwritten characters, the apparatus comprising:

at least one processor operable to recognize a current handwritten stroke intended to be associated with at least one character such that at least one stroke code is associated with the recognized stroke to form a current stroke code sequence, the current stroke code sequence including the current stroke code and previously formed related stroke codes, if such related stroke codes were previously formed, to retrieve from a source of characters one or more entries for display which correspond to the current stroke code sequence, the one or more entries representing one or more candidate characters, to repeat recognition and retrieval if a next stroke is received such that the current stroke code sequence is formed from the stroke code associated with this stroke and stroke codes associated with preceding strokes, and to generate a recognition result associated with the one or more candidate characters if one or more candidate characters are selected as the intended at least one character;

a display coupled to the at least one processor for displaying the one or more entries retrieved from the source of characters at the completion of each stroke; and

memory coupled to the at least one processor for storing at least the character source.

29. An article of manufacture for recognizing handwritten characters comprising a machine readable medium containing one or more programs which when executed implement the steps of:

recognizing a current handwritten stroke intended to be associated with at least one character such that at least one stroke code is associated with the recognized stroke to form a current stroke code sequence, the current stroke code sequence including the current stroke code and previously formed related stroke codes, if such related stroke codes were previously formed;

retrieving from a source of characters one or more entries for display which correspond to the current stroke code sequence, the one or more entries representing one or more candidate characters;

displaying the one or more entries retrieved from the source from the source of characters at the completion of each stroke;

repeating the recognition and retrieval steps if a next stroke is received such that the current stroke code sequence is formed from the stroke code associated with this stroke and stroke codes associated with preceding strokes; and

generating a recognition result associated with the one or more candidate characters if one or more candidate characters are selected as the intended at least one character.