Word recognition method and storage medium that stores word recognition program

• US 6,847,734 B2
• Filed: 01/26/2001
• Issued: 01/25/2005
• Est. Priority Date: 01/28/2000
• Status: Expired due to Term

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Hamamura, Tomoyuki
• Primary Examiner(s): Couso, Yon J.
• Assistant Examiner(s): DESIRE, GREGORY M
• Application Number:
  US09/769,378
• Publication Number:
  US 20010016074A1
• Time in Patent Office: 1,460 Days
• Field of Search: 700/93, 704/240, 704/251, 715/531, 715/541, 382156-161, 382177-179, 382186-189, 382226-231
• US Class Current: 382/229
• CPC Class Codes: G06V 30/2272 with lexical matching

Abstract

In word recognition using the character recognition result, recognition processing is performed for an input character string that corresponds to a word to be recognized, a probability at which characteristics obtained as the result of character recognition are generated by conditioning characters of words contained in a word dictionary that stores in advance candidates of words to be recognized. The thus obtained probability is divided by a probability at which characteristics obtained as the result of character recognition are generated, and each of the division results obtained relevant to the characters of the words contained in the word dictionary is multiplied relevant to all the characters. The recognition results of the above words are obtained based on the multiplication results.

Claims

1. A word identification method comprising:

a character recognition processing step of performing recognition processing of an input character string that corresponds to a word to be recognized by each character, thereby obtaining the character recognition result;

a probability calculation step of obtaining a probability at which characteristics obtained as the character recognition result are generated by said character recognition processing by conditioning characters of words contained in a word dictionary that stores in advance a candidate of the word to be recognized;

a first computation step of dividing the probability obtained by said probability calculation step by a probability of generation of the characteristics obtained as the character recognition result by said character recognition processing step;

a second computation step of performing multiplication for each of division results obtained by said first computation relevant to the characteristics of the words contained in said word dictionary; and

a word recognition processing step of obtaining the recognition result of said word based on multiplication results obtained by this second computation step.

2. A word recognition method according to claim 1, wherein information on characters and non-characters is included in the characters of the words contained in said word dictionary.

3. A word recognition method according to claim 2, wherein a probability at which a word containing information on said non-characters is generated is set based on a probability at which a word that does not contain non-character information is generated.

4. A word recognition method according to claim 1, wherein said character recognition processing step comprises:

delimiting an input character string that corresponds to the word to be recognized by each character;

extracting characteristics of character spacing by this character delimiting; and

performing recognition processing of each character obtained by said character delimiting,

wherein said probability calculation step is used to obtain a probability generated based on the characteristics obtained as the result of character recognition by conditioning the characteristics of characters and character spacing of the words contained in a word dictionary that stores in advance candidates of the characteristics of character spacing in words to be recognized.

5. A storage medium that stores a word recognition program according to claim 4, wherein said step of extracting characteristics of character spacing comprises:

obtaining plural kinds of delimiting results considering whether character spacing is provided or not by character delimiting caused by said character delimiting step; and

extracting characteristics of character spacing relevant to all of the delimiting results obtained by this step.

6. A storage medium that stores a word recognition program according to claim 1, wherein said character recognition processing step comprises:

delimiting an input character string that corresponds to a word to be recognized by each character;

extracting characteristics of character spacing by this character delimiting; and

performing recognition processing of each character obtained by said character delimiting.

7. A storage medium that stores a word recognition program according to claim 6, wherein said step of extracting characteristics of character spacing comprises:

obtaining plural kinds of delimiting results considering whether character spacing is provided or not by character delimiting caused by said character delimiting step; and

extracting characteristics of character spacing relevant to all of the delimiting results obtained by this step.

8. A word identification method comprising:

a character recognition processing step of performing recognition processing of an input character string that corresponds to a word to be recognized by each character, thereby obtaining the character recognition result;

a probability calculation step of obtaining a probability at which characteristics obtained as the character recognition result are generated by said character recognition processing by conditioning characters of words contained in a word dictionary that stores in advance a candidate of the word to be recognized;

a first computation step of performing a predetermined computation between the probability obtained by said probability calculation step and the characteristics obtained as the character recognition result by said character recognition processing step;

a second computation step of performing a predetermined second computation between the computation results obtained by said first computation relevant to the characteristics of the words contained in said word dictionary; and

a word recognition processing step of obtaining the recognition result of said word based on the second computation result by this second computation step,

wherein said character recognition processing step consists of the steps of

delimiting an input character string that corresponds to the word to be recognized by each character;

extracting characteristics of character spacing by this character delimiting; and

performing recognition processing of each character obtained by said character delimiting,

wherein said probability calculation step is used to obtain a probability generated based on the characteristics obtained as the result of character recognition by conditioning the characteristics of characters and character spacing of the words contained in a word dictionary that stores in advance candidates of the characteristics of character spacing in words to be recognized.

9. A word recognition method comprising:

a delimiting step of delimiting an input character string that corresponds to a word to be recognized by each character;

a step of obtaining plural kinds of delimiting results considering whether character spacing is provided or not by character delimiting caused by this delimiting step;

a character recognition processing step of performing recognition processing for each character as all the delimiting results obtained by this step;

a probability calculation step of obtaining a probability at which characteristics obtained as the result of character recognition are generated by said character recognition step by computing the characters of the words contained in the word dictionary that stores in advance candidates of words to be recognized;

a first computation step of performing a predetermined first computation between a probability obtained by this probability computation step and a probability at which characteristics obtained as the result of character recognition are generated by said character recognition processing step;

a second computation step of performing a predetermined computation between computation results obtained by said first computation relevant to each of the characters of the words contained in said word dictionary; and

a word recognition processing step of obtaining the recognition result of said word based on the result of the second calculation caused by this second computation step.

10. A word recognition method according to claim 9, wherein said character recognition step consists of the steps of:

obtaining plural kinds of delimiting results considering whether character spacing is provided or not by character delimiting caused by said character delimiting step;

extracting characteristics of character spacing relevant to all the delimiting results obtained by this step; and

performing recognition processing of each character as all of the said obtained delimiting results, wherein said probability calculation step is used to obtain a probability at which characteristics obtained as the result of character recognition are generated by conditioning characteristics of the characters and character spacing of words contained in the word dictionary that stores in advance candidates of the characteristics of character spacing in words to be recognized.

11. A computer readable storage medium that stores a word recognition program for performing word recognition processing in a computer, wherein said word recognition program contains:

a character recognition processing step of performing recognition processing of an input character string that corresponds to a word to be recognized by each character;

a probability calculation step of obtaining a probability at which characteristics obtained as the character recognition result are generated by said character recognition processing by conditioning characters of words contained in a word dictionary that stores in advance a candidate of the word to be recognized;

a first computation step of dividing the probability obtained by said probability calculation step by a probability of generation of the characteristics obtained as the character recognition result by said character recognition processing step;

a second computation step of performing multiplication for each of division results obtained by said first computation relevant to the characteristics of the words contained in said word dictionary; and

a word recognition processing step of obtaining the recognition result of said word based on multiplication results obtained by this second computation step.

12. A word recognition method according to claim 11, wherein information on characters and non-characters is included in the characters of the words contained in said word dictionary.

13. A word recognition method according to claim 12, wherein a probability at which a word containing information on said non-characters is generated is set based on a probability at which a word that does not contain non-character information is generated.

14. A word recognition method according to claim 11, wherein said character recognition processing step comprises:

delimiting an input character string that corresponds to the word to be recognized by each character;

extracting characteristics of character spacing by this character delimiting; and

performing recognition processing of each character obtained by said character delimiting,

wherein said probability calculation step is used to obtain a probability generated based on the characteristics obtained as the result of character recognition by conditioning the characteristics of characters and character spacing of the words contained in a word dictionary that stores in advance candidates of the characteristics of character spacing in words to be recognized.

15. A storage medium that stores a word recognition program according to claim 14, wherein said step of extracting characteristics of character spacing comprises:

obtaining plural kinds of delimiting results considering whether character spacing is provided or not by character delimiting caused by said character delimiting step; and

extracting characteristics of character spacing relevant to all of the delimiting results obtained by this step.

16. A storage medium that stores a word recognition program according to claim 11, wherein said character recognition processing step comprises:

delimiting an input character string that corresponds to a word to be recognized by each character;

extracting characteristics of character spacing by this character delimiting; and

performing recognition processing of each character obtained by said character delimiting.

17. A storage medium that stores a word recognition program according to claim 16, wherein said step of extracting characteristics of character spacing comprises:

obtaining plural kinds of delimiting results considering whether character spacing is provided or not by character delimiting caused by said character delimiting step; and

extracting characteristics of character spacing relevant to all of the delimiting results obtained by this step.

18. A computer readable storage medium that stores a word recognition program for performing word recognition processing in a computer, wherein said word recognition program contains:

a character recognition processing step of performing recognition processing of an input character string that corresponds to a word to be recognized by each character;

a probability calculation step of obtaining a probability at which characteristics obtained as the character recognition result are generated by said character recognition processing by conditioning characters of words contained in a word dictionary that stores in advance a candidate of the word to be recognized;

a first computation step of performing a predetermined computation between the probability obtained by said probability calculation step and the characteristics obtained as the character recognition result by said character recognition processing step;

a second computation step of performing a predetermined second computation between the computation results obtained by said first computation relevant to the characteristics of the words contained in said word dictionary; and

a word recognition processing step of obtaining the recognition result of said word based on the second computation result by this second computation step,

wherein said character recognition processing step consists of the steps of

delimiting an input character string that corresponds to the word to be recognized by each character;

extracting characteristics of character spacing by this character delimiting; and

performing recognition processing of each character obtained by said character delimiting,

wherein said probability calculation step is used to obtain a probability generated based on the characteristics obtained as the result of character recognition by conditioning the characteristics of characters and character spacing of the words contained in a word dictionary that stores in advance candidates of the characteristics of character spacing in words to be recognized.

19. A storage medium that stores a word recognition program according to claim 18, wherein said step of extracting characteristics of character spacing consists of the steps of:

obtaining plural kinds of delimiting results considering whether character spacing is provided or not by character delimiting caused by said character delimiting step; and

extracting characteristics of character spacing relevant to all of the delimiting results obtained by this step.

20. A computer readable storage medium that stores a word recognition program for performing word recognition processing in a computer, wherein said word recognition program contains:

a character recognition processing step of performing recognition processing of an input character string that corresponds to a word to be recognized by each character;

a probability calculation step of obtaining a probability at which characteristics obtained as the character recognition result are generated by said character recognition processing by conditioning characters of words contained in a word dictionary that stores in advance a candidate of the word to be recognized;

a first computation step of performing a predetermined computation between the probability obtained by said probability calculation step and the characteristics obtained as the character recognition result by said character recognition processing step;

a second computation step of performing a predetermined second computation between the computation results obtained by said first computation relevant to the characteristics of the words contained in said word dictionary; and

a word recognition processing step of obtaining the recognition result of said word based on the second computation result by this second computation step,

wherein said character recognition processing step consists of the steps of;

delimiting an input character string that corresponds to a word to be recognized by each character;

extracting characteristics of character spacing by this character delimiting; and

performing recognition processing of each character obtained by said character delimiting.