| 摘要 |
PROBLEM TO BE SOLVED: To extract a character accurately in each of various types of documents.SOLUTION: A character recognition apparatus 1 includes: a pattern information storage unit 112 which stores the type of a document, an item included in the document, and a character pattern of a character string described for the item, in association with each other; an acquisition unit 121 which acquires image data indicating the document; a specifying unit 122 which specifies the type of the document corresponding to the acquired image data; an extraction unit 123 which extracts an item and a character string corresponding to the item, from an image indicated by the image data, on the basis of the item corresponding to the specified type of the document and the character pattern; and an output unit 124 which outputs the extracted item and character string information indicating the extracted character string, in association with each other.SELECTED DRAWING: Figure 2 |
