Online character recognition system with improved standard strokes processing efficiency

• US 6,035,063 A
• Filed: 06/03/1997
• Issued: 03/07/2000
• Est. Priority Date: 06/03/1996
• Status: Expired due to Term

• Current Assignee: Renesas Electronics Corporation
• Original Assignee: NEC Corporation
• Inventors: Nakashima, Yutaka, Yoshida, Kazunaga, Ikebata, Yoshikazu
• Primary Examiner(s): Bella, Matthew C.
• Application Number:
  US08/868,071
• Time in Patent Office: 1,008 Days
• Field of Search: 382/185, 382/186, 382/187, 382/189, 382/190, 382/195, 382/230, 382/231
• US Class Current: 382/187
• CPC Class Codes: G06V 30/373 using a special pattern or subpattern alphabet

Abstract

An online character recognition system comprises a standard stroke storing unit for storing a standard stroke and its correlated standard stroke number, a standard stroke number of strokes storing unit for storing number of strokes information indicating in how many stroke character each standard stroke appears, a character dictionary storing unit for storing a category to be recognized and its correlated standard stroke number-string, a standard stroke control unit for referring to the standard stroke number of strokes storing unit to selectively read, from the standard stroke storing unit, a standard stroke having the same number of strokes information as the number of strokes of an input character, an inter-stroke distance calculating unit for calculating an inter-stroke distance between a standard stroke read by said standard stroke control unit and an input stroke, and a matching unit for recognizing an input character based on an inter-stroke distance calculated by the inter-stroke distance calculating unit.

Claims

1. An online character recognition system which calculates an inter-stroke distance between each standard stroke generated in advance by quantizing strokes of a known character and each input stroke of an input character, for recognizing said input character online using the inter-stroke distance, comprising:

first storage means for storing said each standard stroke;

second storage means for storing a plurality of known categories;

third storage means for storing relationship data, wherein said relationship data specifies at least one relationship between said each standard stroke stored in said first storage means and said known categories in which said each standard stroke appears;

standard stroke control means for detecting input stroke data of said input character, wherein said input character is comprised of a sequence of input strokes, and wherein said standard stroke control means compares said input stroke data with said relationship data stored in said third storage means, and selects corresponding standard strokes, stored in said first storage means, whose said relationship data is in accord with said input stroke data;

inter-stroke distance calculating means for calculating an inter-stroke distance between the corresponding standard strokes read by said standard stroke control means and said each input stroke; and

character recognition means for recognizing said input character based on the inter-stroke distance calculated by said inter-stroke distance calculating means.

2. The online character recognition system as set forth in claim 1, wherein

said third storage means stores, as relationship data, a list of stroke totals for said each standard stroke, wherein each of said stroke totals represents a total number of strokes which make up each of the known categories in which said each standard stroke appears;

wherein said input stroke data includes an input quantity of strokes contained in said input character; and

wherein said standard stroke control means references said list of stroke totals stored in said third storage means to selectively read, from said first storage means, each of said corresponding standard strokes whose said list of stroke totals includes the input quantity of strokes of said input character.

3. The online character recognition system as set forth in claim 1, wherein

said third storage means stores, as relationship data, a list of stroke orders for said each standard stroke, and wherein each of said stroke orders represents a position, of said each standard stroke, in a standard writing sequence used to compose each of the known categories in which said each standard stroke appears;

wherein said input stroke data includes sequence information corresponding to said each input stroke in said sequence of input strokes; and

wherein said standard stroke control means references said list of stroke orders stored in said third storage means to selectively read, from said first storage means, each of said corresponding standard strokes whose said list of stroke orders includes the sequence information corresponding to said each input stroke in said input character.

4. The online character recognition system as set forth in claim 1, wherein

said third storage means stores, as relationship data, a list of stroke orders for said each standard stroke, and wherein each of said stroke orders represents a position, of said each standard stroke, in a standard writing sequence used to compose each of the known categories in which said each standard stroke appears;

wherein said input stroke data includes sequence information corresponding to said each input stroke in said sequence of input strokes;

wherein said standard stroke control means, with respect to said sequence of input strokes of a single input character, references said list of stroke orders stored in said third storage means to selectively read, from said first storage means, each of said corresponding standard strokes whose said list of stroke orders includes the sequence information corresponding to said each input stroke in said single input character; and

said inter-stroke distance calculating means calculates said inter-stroke distance between said each corresponding standard stroke of a selected character read by said standard stroke control means and said each input stroke of said single input character.

5. The online character recognition system as set forth in claim 1, wherein

said third storage means stores, as relationship data, a list of stroke orders for said each standard stroke, and wherein each of said stroke orders represents a position, of said each standard stroke, in a standard writing sequence used to compose each of the known categories in which said each standard stroke appears;

wherein said input stroke data includes sequence information corresponding to said each input stroke in said sequence of input strokes;

wherein said standard stroke control means, with respect to each of a plurality of sequences of input strokes of input characters, references said list of stroke orders stored in said third storage means to selectively read, from said first storage means, each of said corresponding standard strokes whose said list of stroke orders includes the sequence information corresponding to said each input stroke in said input character; and

said inter-stroke distance calculating means calculates, with respect to each of said sequences of input strokes, said inter-stroke distance between said each corresponding standard stroke read by said standard stroke control means and said each input stroke of said input character.

6. The online character recognition system as set forth in claim 1, wherein

said third storage means stores, as relationship data, a list of stroke totals for said each standard stroke and a list of stroke orders for said each standard stroke, wherein each of said stroke totals represents a total number of strokes which make up each of the known categories in which said each standard stroke appears, and wherein each of said stroke orders represents a position, of said each standard stroke, in a standard writing sequence used to compose each of the known categories in which said each standard stroke appears;

wherein said input stroke data includes an input quantity of strokes contained in said input character, and sequence information corresponding to said each input stroke in said sequence of input strokes; and

said standard stroke control means references said list of stroke totals and said list of stroke orders stored in said third storage means to selectively read, from said first storage means, each of said corresponding standard strokes whose said list of stroke totals includes the input quantity of strokes of said input character and whose said list of stroke orders includes the sequence information corresponding to said each input stroke in said input character.

7. The online character recognition system as set forth in claim 1, wherein

said third storage means includes stroke totals storing means for storing, as relationship data, a list of stroke totals for said each standard stroke, wherein each of said stroke totals represents a total number of strokes which make up each of the known categories in which said each standard stroke appears, and stroke order storing means for storing also as relationship data, a list of stroke orders for said each standard stroke, and wherein each of said stroke orders represents a position, of said each standard stroke, in a standard writing sequence used to compose each of the known categories in which said each standard stroke appears;

wherein said input stroke data includes an input quantity of strokes contained in said input character, and sequence information corresponding to said each input stroke in said sequence of input strokes; and

said standard stroke control means references said list of stroke totals stored in said stroke totals storing means and said list of stroke orders stored in said stroke order storing means to selectively read, from said first storage means, each of said corresponding standard strokes whose said list of stroke totals includes the input quantity of strokes of said input character and whose said list of stroke orders includes the sequence information corresponding to said each input stroke in said input character.

8. The online character recognition system as set forth in claim 1, wherein

said input stroke data includes an input quantity of strokes contained in said input character;

wherein said second storage means also stores a standard stroke number-string for each of said known categories, wherein said standard stroke number-string represents a standard stroke sequence in which said each known category is normally written;

wherein each of said plurality of known categories has a category stroke count, and with respect to said known categories whose stroke count is the same as said input quantity of strokes of said input character, out of the known categories stored in said second storage means, said character recognition means calculates a sum of inter-stroke distances between said each input stroke in said sequence of input strokes and a sequentially corresponding standard stroke listed in said standard stroke number-string for each of the known categories whose stroke count is the same as said input quantity of strokes, and takes a matching category whose said sum of inter-stroke distances is the smallest as a recognition result.

9. The online character recognition system as set forth in claim 1, wherein

said input stroke data includes an input quantity of strokes contained in said input character;

wherein said second storage means also stores a standard stroke number-string for each of said known categories, wherein said standard stroke number-string represents a standard stroke sequence in which said each known category is normally written;

wherein each of said plurality of known categories has a category stroke count, and wherein a count match group is comprised of those known categories whose stroke count is the same as said input quantity of strokes of said input character, out of the known categories stored in said second storage means, and wherein said character recognition means generates a plurality of rearranged standard stroke number-strings by rearranging the order of said standard stroke sequence of said standard stroke number-string for each of the known categories in said count match group, calculates a plurality of sums of inter-stroke distances between said each input stroke in said sequence of input strokes and a plurality of sequentially corresponding standard strokes listed in said standard stroke number string and said plurality of rearranged standard stroke number strings of each of the known categories in said count match group, and takes a matching category having a smallest sum of inter-stroke distances as a recognition result.

10. An online character recognition system which calculates an inter-stroke distance between each stored standard stroke generated in advance by quantizing strokes of a known character and each input stroke of an input character, for recognizing said input character online using the inter-stroke distance, comprising:

a first storage area for storing a plurality of standard strokes;

a second storage area for storing a plurality of known characters;

a third storage area for storing relationship data, wherein said relationship data specifies at least one relationship between each of said plurality of standard strokes stored in said first storage area and a group of said known characters in which said each standard stroke appears;

a standard stroke control device for analyzing a sequence of input strokes of said input character to determine input stroke data, and wherein said standard stroke control device compares said input stroke data with said relationship data stored in said third storage area, and selects corresponding standard strokes from said first storage area whose said relationship data is in accord with said input stroke data;

an inter-stroke distance calculating device for calculating inter-stroke distances between the corresponding standard strokes read by said standard stroke control device and said each input stroke; and

a character recognition device for recognizing said input character based on the inter-stroke distances calculated by said inter-stroke distance calculating device.

11. An online character recognition system as claimed in claim 10, wherein said relationship data includes a list of stroke totals for each of said plurality of standard strokes, and wherein each of said stroke totals represents a total number of strokes constituting each of the known characters in which said each standard stroke appears.

12. An online character recognition system as claimed in claim 10, wherein said relationship data includes a list of stroke orders for each of said standard strokes, and wherein each of said stroke orders represents a position, of said each plurality of standard stroke, in a standard writing sequence used to compose each of the known characters in which said each standard stroke appears.

13. An online character recognition system as claimed in claim 10, wherein said input stroke data includes:

an input quantity of strokes contained in said input character; and

sequence information corresponding to said each input stroke in said sequence of input strokes.