Character recognition technique

• US 6,185,332 B1
• Filed: 04/22/1999
• Issued: 02/06/2001
• Est. Priority Date: 04/22/1999
• Status: Expired due to Term

• Current Assignee: Faxtrieve, Inc.
• Original Assignee: Faxtrieve, Inc.
• Inventors: Thompson, Archie L., Van Saun, Richard A.
• Primary Examiner(s): CHANG, JON CARLTON
• Application Number:
  US09/296,933
• Time in Patent Office: 656 Days
• Field of Search: 382/209, 382/217, 382/218, 382/219, 382/220, 382/221, 382/222, 382/186
• US Class Current: 382/186
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/18095 Summing image-intensity values; Projection and histogram analysis

Abstract

The present invention includes a method, a computer product and a system each of which features fitting a spatial recognition technique to enable a microprocessor to recognize hand-written characters, referred to herein as a cipher. This is achieved by fitting the cipher to a matrix having a plurality of cells with each cell having a plurality of pixels corresponding thereto and determining whether said cipher may be equally distributed among the plurality of cells. In this fashion, a subset of the pixels of a subgroup of the plurality of cells have a sub-portion of the cipher associated therewith and it is determined whether the number of pixels associated with each portion of the cipher are equal. If not, cells have excess pixels associated with a portion of the cipher, compared to other cells in the matrix, have the excess pixels assigned to a different cell. This facilitates creating a digital word that describes the cipher that is then compared with information in a look-up table. The digital information of each entry in the look-up table is compared with the digital word. A fuzzy logic algorithm determines the closest matches in the look-up table, and the cipher that corresponds to the closest match is identified.

Claims

1. A method for recognizing a cipher, said method comprising:

associating said cipher with a plurality of cells of a matrix having N rows and M columns, with each of said plurality of cells having a plurality of pixels corresponding thereto, with a subset of said plurality of pixels, of a subgroup of said plurality of cells, having a portion of said cipher associated therewith, defining a plurality of portions of said cipher, wherein subsets of said plurality of pixels having a number of pixels associated therewith in excess of a number of pixels associated with the remaining subsets, defining remainder pixels, are positioned in predetermined cells of said matrix;

determining whether each of said subset of pixels includes an equal number of pixels;

assigning a binary state identifier with each cell of said plurality of cells;

assigning a digital word to said matrix, with said digital word being a function of the binary state of said plurality of cells, wherein said assigning includes forming digital data which corresponds to said predetermined position, with said digital work including said digital data;

comparing said digital word with information in a look-up table, said information including a plurality of known ciphers, each of which includes a corresponding digital representation; and

providing the known cipher corresponding to the digital representation in said look-up table that most closely matches said digital word.

2. The method as recited in claim 1 wherein comparing said digital word includes comparing a sub-portion of said digital word with said information, with said sub-portion corresponding to said binary state of pixels in a single row of said matrix.

3. The method as recited in claim 1 wherein said information includes user defined data.

4. The method as recited in claim 1 wherein said cipher includes opposed ends and sub-portions of said digital word includes information corresponding to spatial positions of said opposed ends.

5. The method as recited in claim 1 wherein comparing said digital word with information in said look-up table includes comparing a sub-portion of said digital word with said information, with said sub-portion corresponding to said binary state of pixels in a single row of said matrix for each row in said matrix and obtaining a final value, with said final value being a function of a difference characteristic between said digital word and said digital representation.

6. The method as recited in claim 1 wherein comparing said digital word with each digital representation in said look-up table includes obtaining multiple final values, each of said multiple final values being a function of a difference characteristic between said digital word and said digital representation and providing said known cipher corresponding to the digital representation in said look-up table including providing said known cipher associated with the digital representation corresponding to a subset of said multiple final values, said subset including final values having a least magnitude of said multiple final values.

7. The method as recited in claim 1 wherein comparing said digital word with each digital representation in said look-up table includes obtaining multiple final values, each of said multiple final values being a function of a difference characteristic between said digital word and said digital representation and providing said known cipher corresponding to the digital representation in said look-up table including providing said known cipher associated with the digital representation corresponding to each of a subset of said multiple final values, said subset including final values having a least magnitude of said multiple final values and further including distinguishing between multiple final values of said subset by associating a fitness value with each of the final value of said subset, with said fitness value being a function of a number of times a digital representation is associated with one of said multiple values of said subset.

8. The method as recited in claim 1 wherein N equals M.

9. The method as recited in claim 1 wherein said binary state is a one (1) or a zero (0).

10. A computer program product that controls a computer to recognize a cipher, said computer program product comprising a computer readable medium encoded with code comprising:

code to associate said cipher with a plurality of cells of a matrix having N rows and M columns, with each of said plurality of cells having a plurality of pixels corresponding thereto, with a subset of said plurality of pixels, of a subgroup of said plurality of cells, having a portion of said cipher associated therewith, defining a plurality of portions of said cipher, wherein subsets of said plurality of pixels having a number of pixels associated therewith in excess of a number of pixels associated with the remaining subsets, defining remainder pixels, are positioned in predetermined cells of said matrix;

code to determine whether each of said subset of pixels includes an equal number of pixels;

code to assign a binary state identifier with each cell of said plurality of cells;

code to assign a digital word to said matrix, with said digital word being a function of the binary state of plurality of cells, wherein said code to assign a digital word to said matrix includes code to form digital data which corresponds to said predetermined position, with said digital word including said digital data;

code to compare said digital work with information in a look-up table, said information including a plurality of known ciphers, each of which includes a corresponding digital representation; and

code to provide the known cipher corresponding to the digital representation in said look-up table that most closely mataches said digital word.

11. The computer program product as recited in claim 10 wherein said code to compare said digital word includes code to compare a sub-portion of said digital word with said information, with said sub-portion corresponding to said binary state of pixels in a single row of said matrix.

12. The computer program product as recited in claim 10 wherein said information includes user defined data.

13. The computer program product as recited in claim 10 wherein said cipher includes opposed ends and sub-portions of said digital word includes information corresponding to spatial positions of said opposed ends.

14. The computer program product as recited in claim 10 wherein said code to compare said digital word with information in said look-up table includes code to compare a sub-portion of said digital word with said information, with said sub-portion corresponding to said binary state of pixels in a single row of said matrix for each row in said matrix and obtaining a final value, with said final value being a function of a difference characteristic between said digital word and said digital representation.

15. The computer program product as recited in claim 10 wherein said code to compare said digital word with each digital representation in said look-up table includes code to obtain multiple final values, each of said multiple final values being a function of a difference characteristic between said digital word and said digital representation and said code to provide said known cipher corresponding to the digital representation in said look-up table including code to provide said known cipher associated with the digital representation corresponding to a subset of said multiple final values, said subset including final values having a least magnitude of said multiple final values.

16. The computer program product as recited in claim 10 wherein code to compare said digital word with each digital representation is said look-up table includes code to obtain multiple final values, each of said multiple final values being a function of a difference characteristic between said digital word and said digital representation and said code to provide said known cipher corresponding to the digital representation in said look-up table includes code to provide said known cipher associated with the digital representation corresponding to each of a subset of said multiple final values, said subset including final values having a least magnitude of said multiple final values and further including distinguishing between multiple final values of said subset by associating a fitness value with each of the final values of said subset, with said fitness value being a function of a number of times a digital representation is associated with one of said multiple values of said subset.

17. The computer program product as recited in claim 10 wherein N equals M.

18. The computer program product as recited in claim 10 wherein said binary state is a one (1) or a zero (0).

19. A system for recognizing a cipher comprising:

means for associating said cipher with a plurality of cells of a matrix having N rows and M columns, with each of said plurality of cells having a plurality of pixels corresponding thereto, with a subset of said plurality of pixels, of a subgroup of said plurality of cells, having a portion of said cipher associated therewith, defining a plurality of portions of said cipher, wherein subsets of said plurality of pixels having a number of pixels associated therewith in excess of a number of pixels associated with the remaining subsets, defining remainder pixels, are positioned in predetermined cells of said matrix;

means, in data communication with said means for associating, for determining whether each of said subset of pizels includes an equal number of pixels;

means, in data communication with said means for determining, for assigning a binary state identifier with each cell of said plurality of cells;

means, in data communication with said means for assigning a binary state identified, for assigning a digital word to said matrix, with said digital word being a function of the binary state of said plurality of cells, wherein said means for assigning a digital word to said matrix includes a means for forming digital data which corresponds to said predetermined position, with said digital word including said digital data;

means, in data communication with said means for assigning a digital word, for comparing said digital word with information in a look-up table, said information including a plurality of known ciphers, each of which includes a corresponding digital representation; and

means, in data communication with said means for comparing, for providing the known cipher corresponding to the digital representation in said look-up table that most closely matches said digital word.

20. The system as recited in claim 19 wherein comparing said digital word includes comparing a sub-portion of said digital word with said information, with said sub-portion corresponding to said binary state of pixels in a single row of said matrix.

21. The system as recited in claim 19 wherein said information includes user defined data.

22. The system as recited in claim 19 wherein said cipher includes opposed ends and sub-portions of said digital word includes information corresponding to spatial positions of said opposed ends.

23. The system as recited in claim 19 wherein said means for comparing said digital word with information in said look-up table includes means for comparing a sub-portion of said digital word with said information, with said sub-portion corresponding to said binary state of pixels in a single row of said matrix for each row in said matrix and obtaining a final value, with said final value being a function of a difference characteristic between said digital word and said digital representation.

24. The system as recited in claim 19 wherein means for comparing said digital word with each digital representation in said look-up table includes means for obtaining multiple final values, each of said multiple final values being a function of a difference characteristic between said digital word and said digital representation and means for providing said known cipher corresponding to the digital representation in said look-up table includes means for providing said known cipher associated with the digital representation corresponding to a subset of said multiple final values, said subset including final values having a least magnitude of said multiple final values.

25. The system as recited in claim 19 wherein said means for comparing said digital word with each digital representation in said look-up table includes means for obtaining multiple final values, each of said multiple final values being a function of a difference characteristic between said digital word and said digital representation and said means for providing said known cipher corresponding to the digital representation in said look-up table including means for providing said known cipher associated with the digital representation corresponding to each of a subset of said multiple final values, said subset including final value having a least magnitude of said multiple final values and further including distinguishing between multiple final values of said subset by associating a fitness value with each of the final values of said subset, with said fitness value being a function of a number of times a digital representation is associated with one of said multiple value of said subset.

26. The system as recited in claim 19 wherein N equals M.

27. The system as recited in claim 19 wherein said binary state is a one (1) or a zero (0).