Incremental ideographic character input method

• US 6,148,104 A
• Filed: 01/14/1999
• Issued: 11/14/2000
• Est. Priority Date: 11/15/1996
• Status: Expired due to Term

• Current Assignee: Synaptics Incorporated
• Original Assignee: Synaptics Incorporated
• Inventors: Platt, John C., Matic, Nada P., Wang, Chung-Ning
• Primary Examiner(s): Couso, Jose L.
• Assistant Examiner(s): Do, Anh Hong
• Application Number:
  US09/231,911
• Time in Patent Office: 670 Days
• Field of Search: 382/185, 382/187, 382/189, 382/202, 382/310, 364/926.8
• US Class Current: 382/185
• CPC Class Codes: G06F 3/018 Input/output arrangements for oriental characters
• CPC Class Codes: G06V 30/287 of Kanji, Hiragana or Katakana characters
• CPC Class Codes: G06V 30/347 Sampling; Contour coding; Stroke extraction
• CPC Class Codes: G06V 30/387 using human interaction, e.g. selection of the best displayed recognition candidate

Abstract

A method for incremental recognition of ideographic handwriting comprises in order the steps of: (1) entering in a natural stroke order at least one stroke of an ideographic character from a computer entry tablet; (2) providing the at least one stroke to an incremental character recognizer, which produces a hypothesis list of at least one candidate character; (3) displaying a hypothesis list of candidate characters containing the at least one stroke; (4) selecting a correct character from among the candidate characters on the hypothesis list if it a correct character appears thereon; (5) entering in natural stroke order at least one additional stroke of the ideographic character from the computer entry tablet if no candidate character is a correct character; (6) providing the additional stroke(s) to the incremental character recognizer, which produces an updated hypothesis list; (7) displaying the updated hypothesis list of candidate characters containing every stroke; (8) selecting a correct character from among the candidate characters on the updated hypothesis list if it a correct character appears thereon; and (9) repeating steps (5) through (8) until a correct character is selected from the updated hypothesis list.

Claims

1. Apparatus for incremental recognition of ideographic handwriting comprising:

a computer entry tablet for entering strokes of an ideographic character in natural stroke order;

an incremental character recognizer coupled to said computer entry tablet, responsive to partial characters, that generates an hypothesis list of at least one candidate character containing said strokes;

means for displaying said hypothesis list;

means for selecting a correct character from among said at least one candidate character of said hypothesis list;

means for providing at least one additional individual stroke in natural stroke order to said incremental character recognizer if none of said at least one candidate character of said hypothesis list have been selected.

2. The apparatus of claim 1, wherein said incremental character recognizer comprises:

a pre-processor, and

a statistical pattern classifier.

3. The apparatus of claim 2, wherein said statistical pattern classifier comprises at least one standard neural network layer.

4. The apparatus of claim 2, wherein said statistical pattern classifier comprises a time-delay neural network.

5. The apparatus of claim 1, wherein said incremental character recognizer comprises:

a plurality of detailed classifiers, each detailed classifier recognizing a subset of possible characters;

a pre-classifier, which selects one of the plurality of detailed classifiers to use.

6. The apparatus of claim 1, wherein said incremental character recognizer further includes means for manipulating said hypothesis list of candidate characters.

7. The apparatus of claim 6, wherein said means for manipulating said hypothesis list of candidate characters comprises means for deleting hypothesis.

8. The apparatus of claim 6, wherein said means for manipulating said hypothesis list of candidate characters comprises means for inserting hypothesis.

9. The apparatus of claim 6, wherein said means for manipulating said hypothesis list of candidate characters comprises means for re-ordering the hypothesis.

10. An apparatus for the incremental recognition ideographic characters, comprising

an input device for the input of coordinate data representing strokes of an ideographic character;

an input processor for the processing of said coordinate data;

an incremental recognizer that is responsive to partial characters and generates a hypothesis list of at least one candidate character;

a display device;

a window on said display device which is divided into a first region for displaying strokes and a second region for displaying said at least one candidate character.

11. The apparatus of claim 10, wherein said input device is a touchpad that is smaller than 3 inches in width and height.

12. The apparatus of claim 10, where the entire coordinate system of said input device is mapped into the entire coordinate system of said window.

13. The apparatus of claim 10, wherein said window further includes a region for the display of commands.

14. The apparatus of claim 13, wherein said command region lies along the edge of said window.

15. The apparatus of claim 13, wherein said second region for displaying said at least one candidate character lies along the edge of said window.

16. The apparatus of claim 13, wherein said stroke region is divided into a plurality of sub-regions, said input processor responsive to coordinate input in said plurality of sub-regions.

17. A method for incremental recognition of ideographic handwriting comprising in order the steps of:

(1) entering at least one stroke of an ideographic character from a computer entry tablet;

(2) providing said at least one stroke to an incremental character recognizer including a pre-processor and a statistical pattern classifier, said incremental recognizer producing a hypothesis list of at least one candidate character;

(3) displaying said hypothesis list of candidate characters containing said at least one stroke;

(4) selecting a correct character from among said candidate characters on said hypothesis list if it a correct character appears thereon;

(5) entering at least one additional stroke of said ideographic character from said computer entry tablet if no candidate character is a correct character;

(6) providing said at least one additional stroke to said incremental character recognizer and producing an updated hypothesis list of at least one candidate character;

(7) displaying said updated hypothesis list of candidate characters containing every stroke;

(8) selecting a correct character from among said candidate characters on said updated hypothesis list if it a correct character appears thereon; and

(9) repeating steps (5) through (8) until a correct character is selected from said updated hypothesis list.

18. The method of claim 17, wherein said statistical pattern classifier comprises at least one standard neural network layer.

19. The method of claim 17, wherein said statistical pattern classifier comprises a time-delay neural network.

20. The method of claim 17, wherein said incremental character recognizer comprises:

a plurality of detailed classifiers, each detailed classifier recognizing a subset of possible characters;

a pre-classifier, which selects one of the plurality of detailed classifiers to use.

21. The method of claim 17, wherein said step of producing said updated hypothesis list includes the step of deleting at least one of said candidate characters from said hypothesis list.

22. The method of claim 17, of wherein said step of producing an updated hypothesis list includes the step of inserting at least one additional candidate character said hypothesis list.

23. The method of claim 17, wherein said candidate characters have an order and wherein said step of producing an updated hypothesis list includes the step of re-ordering at least one of said candidate characters on said updated hypothesis list.

24. A method for incremental recognition of ideographic handwriting comprising in order the steps of:

(1) entering at least one stroke of an ideographic character in natural stroke order from a computer entry tablet;

(2) providing said at least one stroke to an incremental character recognizer including a pre-processor and a statistical pattern classifier, said incremental recognizer producing a hypothesis list of at least one candidate character;

(3) displaying said hypothesis list of candidate characters containing said at least one stroke;

(4) selecting a correct character from among said candidate characters on said hypothesis list if it a correct character appears thereon;

(5) entering at least one additional stroke of said ideographic character in natural stroke order from said computer entry tablet if no candidate character is a correct character;

(6) providing said at least one additional stroke to said incremental character recognizer and producing an updated hypothesis list of at least one candidate character;

(7) displaying said updated hypothesis list of candidate characters containing every stroke;

(8) selecting a correct character from among said candidate characters on said updated hypothesis list if it a correct character appears thereon; and

(9) repeating steps (5) through (8) until a correct character is selected from said updated hypothesis list.