Character recognition apparatus, character recognition method, and computer readable medium storing program
View Patent ↗A character recognition apparatus includes an acquisition unit, a specification unit, a movement unit, and a recognition unit. The acquisition unit acquires data representing a character string. The specification unit specifies an element of a compound character satisfying a predetermined condition for determining the compound character from the character string. The movement unit moves the element of the compound character close to an adjacent character. The recognition unit recognizes a changed character string in which the movement unit has moved the element of the compound character, based on a shape of characters and relevance between adjacent characters.
1. A character recognition apparatus comprising:
an acquisition unit that acquires data representing a character string written in a plurality of separate areas of a character recognition device;
a memory that stores the data representing the character string;
a specification unit that specifies an element of a compound character satisfying a predetermined condition for determining the compound character from the character string;
a movement unit that moves the element of the compound character close to an adjacent character;
a recognition unit that recognizes a changed character string in which the movement unit has moved the element of the compound character, based on a shape of characters and relevance between adjacent characters; and
an integration unit that integrates the plurality of separate areas, wherein
the integration unit integrates an area where the moved element of the compound character is written and an area where the adjacent character is written, and
the recognition unit specifies recognition candidates as a single character based on the shape of the character to be recognized when the character to be recognized is written in an area that is not integrated by the integration unit, and specifies the recognition candidates as the single character or as a plurality of characters based on the shape of the character to be recognized when the character to be recognized is written in an area that is integrated by the integration unit.
2. The character recognition apparatus according to claim 1 , wherein the memory that stores a value indicating appearance probability of a second character that follows a first character, and
wherein the recognition unit recognizes the changed character string, by specifying a plurality of candidates of the second character based on a shape of the characters, and by selecting a character having highest appearance probability from the candidates in accordance with the value stored in the memory.
3. The character recognition apparatus according to Claim 1 , wherein the element of the compound character is a diacritical mark, and
the movement unit moves the diacritical mark close to the adjacent character.
4. The character recognition apparatus according to claim 2 , wherein the element of the compound character is a diacritical mark, and
the movement unit moves the diacritical mark close to the adjacent character.
5. The character recognition apparatus according to claim 1 , wherein the element of the compound character is a diacritical mark, and
the movement unit moves the diacritical mark close to the adjacent character.
6. The character recognition apparatus according to Claim 1 , wherein the predetermined condition includes a position of a character and a number of strokes of a character.
7. The character recognition apparatus according to claim 3 , wherein the predetermined condition includes a position of a character and a number of strokes of a character.
8. The character recognition apparatus according to claim 4 , wherein the predetermined condition includes a position of a character and a number of strokes of a character.
9. The character recognition apparatus according to claim 5 , wherein the predetermined condition includes a position of a character and a number of strokes of a character.
10. The character recognition apparatus according to claim 1 , wherein the movement unit moves the element of the compound character close to the adjacent character in a horizontal direction or in a vertical direction.
11. The character recognition apparatus according to claim 1 , wherein the acquisition unit acquires data representing the character string from image data.
12. The character recognition apparatus according to claim 11 , wherein the image data includes handwriting data.
13. A character recognition method comprising:
acquiring data representing a character string written in a plurality of separate areas of a character recognition device;
storing the data representing the character string in a memory;
specifying an element of a compound character satisfying a predetermined condition for determining the compound character from the character string;
moving the element of the compound character close to an adjacent character;
recognizing a changed character string in which the element of the compound character has been moved, based on a shape of characters and relevance between adjacent characters; and
integrating the plurality of separate areas,
wherein the integrating integrates an area where the moved element of the compound character is written and an area where the adjacent character is written, and
wherein the recognizing specifies recognition candidates as a single character based on the shape of the character to be recognized when the character to be recognized is written in an area that is not integrated by the integrating, and specifies the recognition candidates as the single character or as a plurality of characters based on the shape of the character to be recognized when the character to be recognized is written in an area that is integrated by the integrating.
14. A non-transitory computer readable medium storing a program causing a computer to execute a process, the process comprising:
acquiring data representing a character string written in a plurality of separate areas of a character recognition device;
storing the data representing the character string in a memory;
specifying an element of a compound character satisfying a predetermined condition for determining the compound character from the character string;
moving the element of the compound character close to an adjacent character;
recognizing a changed character string in which the element of the compound character has been moved, based on a shape of characters and relevance between adjacent characters; and
integrating the plurality of separate areas,
wherein the integrating integrates an area where the moved element of the compound character is written and an area where the adjacent character is written, and
wherein the recognizing specifies recognition candidates as a single character based on the shape of the character to be recognized when the character to be recognized is written in an area that is not integrated by the integrating, and specifies the recognition candidates as the single character or as a plurality of characters based on the shape of the character to be recognized when the character to be recognized is written in an area that is integrated by the integrating.