On-line handwritten character recognition apparatus with non-ambiguity algorithm

• US 5,034,989 A
• Filed: 01/17/1989
• Issued: 07/23/1991
• Est. Priority Date: 12/11/1987
• Status: Expired due to Fees

• Current Assignee: Shiu-Chang Loh
• Original Assignee: Shiu-Chang Loh
• Inventors: Loh, Shiu-Chang
• Primary Examiner(s): Razavi, Michael
• Application Number:
  US07/298,566
• Time in Patent Office: 917 Days
• Field of Search: 382/13, 382/38, 382/3, 382/24, 382/40, 382/57, 382/10, 382/11, 178/18, 178/19, 178/20, 178/30
• US Class Current: 382/189
• CPC Class Codes: G06V 30/347 Sampling; Contour coding; Stroke extraction
• CPC Class Codes: G06V 30/373 using a special pattern or subpattern alphabet

Abstract

An apparatus and a method for identifying handwritten characters is provided, each of the characters being a member of a set and being formed from a number of predetermined primitives. The apparatus includes an input device receiving successively each primitive forming a character. The input device generates input signals for each primitive forming the handwritten character. The input signals are conveyed to a processor. The processor examines the input signals and attempts to identify each of the primitives used to form the handwritten character. A primitive code is generated for each identified primitive and an unidentified primitive code is generated for each unidentified primitive. The primitive and unidentified primitive codes are combined to form an input character code. A memory is provided and stores a character code and an international output code for each of the characters in the set of characters. A comparator compares the input character code generated for the handwritten character with each of the character codes stored in the memory. When the input character code is equivalent to a character code associated with only one output code, the output code is conveyed to an output device such as a printer wherein a reproduction of the handwritten character is formed. When the character code is equivalent to a character code associated with more than one output code, a differentiator detects the correct output code associated with the input character code so that the handwritten character can be reproduced.

Claims

1. A character recognition apparatus for identifying a handwritten of a predetermined set of characters formed from at least one primitive selected from a predetermined set of primitives illustrated in FIG. 3 with said set of primitives forming said handwritten character being written in an order determined by pre-defined rules, said apparatus comprising:

input means for receiving successively and in accordance with said pre-defined rules each of the primitives forming said handwritten character and generating input signals for each of said received primitives;

processing means for receiving said input signals and identifying each of said primitives received by said input means, said processing means generating a character code representing said handwritten character upon identification of said primitives forming said handwritten character;

storage means for storing a character code and an associated output code for each of the characters in said predetermined set;

comparing means for comparing said character code generated for said handwritten character with said character codes in said storage means to identify said handwritten character; and

output means in communication with said comparing means and generating a reproduction of said handwritten character upon the identification thereof by said comparing means.

2. The character recognition apparatus as defined in claim 1 further comprising:

differentiation means for examining said input signals generated for each of said received primitives and performing operations thereon when said character code generated for said handwritten character is equivalent to a character code in said storage means associated with a plurality of output codes to identify the output code associated with said handwritten character.

3. The character recognition apparatus as defined in claim 2 wherein said primitives in FIG. 3 are capable of forming every character in a plurality of languages while reducing the number of characters in said languages formed from the same series of primitives, said storage means storing a character code and an output code for each of said characters in said plurality of languages.

4. The character recognition apparatus as defined in claim 3 wherein said storage means further stores character test information, said test information being provided for each character code in said storage means associated with more than one output code, said differentiation means receiving said character test information and said input signals and performing said operations thereon in accordance with said character test information to detect the output code corresponding to said handwritten character.

5. The apparatus as defined in claim 3 wherein said processing means generated an unidentified primitive code for each handwritten primitive not detected as being in said set, said apparatus further comprising substitution means having means for receiving said character code generated for said handwritten character when it is not equivalent to any of said character codes in said storage means, said substitution means including comparator means comparing each primitive code forming character code generated for said handwritten character with the corresponding primitive code of said character codes in said storage means formed from the same number of primitive codes as the character code generated for said handwritten character;

and

a memory for storing the output code associated with each of the character codes in said storage means having fewer than a predetermined number of differences when compared with character code generated for said handwritten character.

6. The apparatus as defined in claim 5 wherein said substitution means further comprises a probability matrix, said probability matrix generating a substitution primitive code most likely to be the unidentified primitive code when said substitution means receives a character code generated for a handwritten character having at least one unidentified primitive code therein and replacing said unidentified primitive code with said substitution primitive code to form a character code equivalent to a character code stored in said storage means, and most likely to represent said handwritten character.

7. The apparatus as defined in claim 1 wherein said input means is an on-line digitizer tablet providing cartesian co-ordinate data for each of said primitives forming said handwritten character, said processing means further comprising encoding means for examining said cartesian co-ordinate data for each of said primitives forming said handwritten character and forming therefrom a series of unit vectors.

8. The apparatus as defined in claim 7 wherein said encoding means is a modified Freeman encoder which includes a plurality of freeman unit vectors, said encoder detecting only substantially vertical, horizontal and diagonal strokes forming the primitives constituting said handwritten character.

9. The apparatus as defined in claim 8 wherein said processing means further comprises:

feature extraction means for receiving said series of unit vectors for each of said primitives and eliminating redundant unit vectors to form a vector code and an associated series of scalars for each of said handwritten primitives;

holding means for storing vector codes and an associated primitive code representing each of said primitives in said set along with an unidentified primitive code; and

comparator means for comparing said vector codes generated for said handwritten character with said vector codes stored in said holding means, said comparator means generating said primitive code when said vector code is equivalent to a vector code stored in said holding means and generating said unidentified primitive code when said vector code is not equivalent to a vector code stored in said holding means.

10. The apparatus as defined in claim 9 wherein said holding means is further provided with primitive test information, said information being uniquely associated with vector codes which represent more than one primitive in said set, said processing means further comprising a test section receiving said primitive test information and said series of scalars associated with said vector code and performing operations thereon to detect the correct primitive code associated with said vector code generated for said handwritten the primitive when said vector code is equivalent to a vector code representing more than one primitive.

11. The apparatus as defined in claim 1 wherein said output means is selected form the group comprising:

a printer, an audio-synthesizer and a video display terminal.

12. An apparatus as defined in claim 9 further comprising pre-processing means for receiving said cartesian co-ordinate data, said preprocessing means comparing the distance between first and adjacent second co-ordinates and removing said second co-ordinate if said distance is less than a predetermined threshold value thereby reducing the amount of redundant data.

29. The character recognition apparatus as defined in claim 4 wherein said test information causes said differentiation means to determine the relative length between two primitives forming said handwritten character or whether one primitive forming the handwritten character crosses another.

30. The character recognition apparatus as defined in claim 10 wherein said test section examines said vector codes to determine the relative length of the vector codes generated for the handwritten character.

13. A method of identifying a handwritten character of a pre-determined set of characters formed from at least one primitive selected from the set of primitives shown in FIG. 3, said method comprising the steps of:

receiving successively and in an order determined by pre-define rules each of said primitives forming said character and generating input signals for each of said received primitives;

examining said input signals to identify each of said entered primitives forming said handwritten character;

generating a primitive code for each of said primitives forming said handwritten character to form a character code upon identification of said primitives forming said handwritten character;

storing a character code and an associated output code for each of said characters in said set;

comparing said character code formed for said handwritten character with said character codes stored to detect said output code when said character code generated for said handwritten character is equivalent to a stored character code associated with only one output code; and

examining said primitive codes generated for said handwritten character and performing operations thereon when said character code is equivalent to a stored character code associated with more than one output code in order to detect the output code associated with said entered character; and

generating an image of said handwritten character upon detection of said associated output code.

14. A character recognition apparatus for identifying a handwritten character formed from at least one primitive, said character and said primitives being members of predetermined sets, said apparatus comprising:

input means for receiving successively and in order determined by pre-defined rules, each of the handwritten primitives forming said handwritten character said input means generating input signals for each of said handwritten primitives;

processing means receiving said input signals for each of said primitives, said processing means converting the input signals generated for each primitive into data representing a series of generally horizontal, vertical and diagonal vectors and comparing said data with stored information therein and generating a primitive code for each of the primitives when said data are detected as being equivalent to stored information associated with a single primitive;

first differentiation means in communication with said processing means and performing discriminatory tests on said data when said data are detected as being equivalent to stored information associated with a plurality of primitives to determine the primitive associated with said data to permit said processing means to determine said primitive code, the series of primitive codes generated by said processing means forming a character code;

storage means storing a character code and an associated output code for each of the characters in said predetermined set;

comparing means comparing said character code generated for said handwritten character with said character codes in said storage means to identify said entered handwritten character;

second differentiation means examining said input signals generated for each of said handwritten primitives and performing discriminatory tests thereon when said character code generated for said handwritten character is equivalent to a character code in said storage means associated with a plurality of output codes to identify the output code associated with said handwritten character; and

output means in communication with said comparing means and said second differentiation means and generating a reproduction of said handwritten character upon identification of the output code associated with the handwritten character.

15. The character recognition apparatus as defined in claim 14 wherein said primitives are capable of forming substantially every character in a plurality of languages, said storage means storing a character code and an output code for each of said characters in said plurality of languages.

16. The character recognition apparatus as defined in claim 15 wherein said storage means further stores character test information, said test information being provided for each character code associated with more than one output code, said second differentiation means receiving said character test information and said output signals and performing said discriminatory test on said input signals in accordance with said character test information to detect the output code corresponding to said handwritten character.

17. The character recognition apparatus a defined in claim 16 wherein said predetermined set of primitives includes twenty distinct primitives, the various combination of said twenty primitives being capable of forming substantially all characters in said plurality of languages, a substantial portion of said primitives being formed from only substantially horizontal, substantially vertical and substantially diagonal components.

18. The character recognition apparatus as defined in claim 17 further comprising:

substitution means receiving the character code generated for said handwritten character when said character code is not equivalent to any of said character codes stored in said storage means, said substitution means including comparator means for comparing each primitive code forming said character code generated for the handwritten character with the corresponding primitive codes forming said character codes in said storage means having the same number of primitive codes as the character code generated for the handwritten character to detect differences between the character code and said character codes in said storage means; and

a memory for storing the output code associated with each of the character codes in said storage means having fewer than a predetermined number of differences when compared with the character code generated for the handwritten character.

19. The character recognition apparatus as defined in claim 18 wherein said processing means generates an unidentified primitive code when said processing means and said first differentiation means do not detect said data as being equivalent to any information stored therein, said unidentified primitive code when generated forming part of said character code, said substitution means further comprising a probability matrix, said probability matrix generating a substitution primitive code most likely to be the unidentified primitive code when said substitution means receives a character code having at least one identified primitive code therein and replacing said unidentified primitive code with said substitution primitive code in an attempt to form a character code equivalent to a character code stored in said storage means and most likely to represent said handwritten character.

20. The character recognition apparatus as defined in claim 14 wherein said input means is an on-line digitizer tablet generating cartesian co-ordinate data for each of said primitives forming said handwritten character, said processing means further comprising encoding means for examining said cartesian co-ordinate data for each of said primitives and forming therefrom a series of vectors and associated series of scalars.

21. The character recognition apparatus as defined in claim 20 wherein said encoding means is a modified Freeman encoder, said encoder examining said series of vectors to detect substantially horizontal, substantially vertical and substantially diagonal unit vectors and converting said series of vectors into said data, said first differentiation means performing discriminatory tests on said associated scalars when said data generated for a primitive forming part of said handwritten character is detected as being equivalent to stored information associated with a plurality of primitives to determine the primitive associated with the data.

22. The character recognition apparatus as defined in claim 21 wherein said processing means further comprises feature extraction means receiving said series of vectors for each of said primitives and eliminating redundant vectors to form said data, said data being in the form of a vector code and said associated series of scalars for each of said handwritten primitives;

holding means for storing vector codes and an associated primitive code representing each of said primitives in said set along with an unidentified primitive code; and

comparator means for comparing said vector codes generated for said handwritten primitive with said vector codes stored in said holding means, said comparator means output said primitive code when said vector code is equivalent to a vector code stored in said holding means and output said unidentified primitive code when said vector code is not equivalent to a vector code stored in said holding means.

23. The apparatus as defined in claim 22 wherein said holding means is further provided with primitive test information, said information being uniquely associated with vector codes which represent more than one primitive, said first differentiation means receiving said primitive test information and said series of scalars associated with said vector code from said processing means and performing operation thereon to detect the correct primitive code associated with said vector code when said vector code is equivalent to a vector code representing more than one primitive code.

24. An apparatus as defined in claim 23 further comprising a pre-processing means for receiving and conditioning said cartesian co-ordinate data to eliminate spurious data and to reduce redundant data.

25. The apparatus defined in claim 14 wherein all primitives are generally horizontal vectors, generally vertical vectors, generally diagonal vectors, or a combination of generally horizontal, vertical and diagonal vectors.

27. The character recognition apparatus as defined in claim 14 wherein the discriminatory tests determine the relative length between two primitives forming said handwritten character or whether one primitive forming the handwritten character crosses another.

28. The character recognition apparatus as defined in claim 21 wherein the discriminatory tests determine the relative length of the vertical, diagonal and horizontal vectors generated for the primitive.

26. A method of identifying a handwritten character formed from at least one primitive, said character and said primitives being members of predetermined sets, said method comprising the steps of:

receiving successively and in an order determined by predefined rules each of said primitives forming said character in a predetermined manner and generating input signals for each of said received primitives;

examining and converting the input signals for each primitive into data representing a series of generally horizontal, vertical and diagonal vectors and comparing said data generated for each of said entered primitives with stored information to identify each of said entered primitives forming said character;

generating a primitive code for each of said primitives when the data are detected as being associated with only one primitive and performing tests on said data to determine the correct primitive code when said data are detected as being associated with more than one primitive;

forming a generated character code from said series of primitive codes;

storing a character code and an associated output code for each of said characters in said set;

comparing the generated character code with said stored character codes to determine said output code when said generated character code is equivalent to a stored character code associated with only one output code;

examining said input signals generated for said entered primitives and performing tests thereon when said generated character code is equivalent to a stored character code associated with more than one output code in order to determine the output code associated with said handwritten character; and

generating an image of said handwritten character upon detection of said correct output code.