摘要 |
PROBLEM TO BE SOLVED: To properly section a recognition result. SOLUTION: The optical character recognition device includes an image storage part 102 which stores electronized document image data, a character recognition part 105 which reads in the document image data and recognizes characters, a section retrieval part 109 which sections the result of the character recognition by the endings of sentences, the endings of words, etc., an output unit determination part 10 which determines units to be outputted to the outside according to the sectioning, an incomplete output unit recording part 111 which records incompletely sectioned output units like final output units, a recognition result output part 107 which outputs the recognition result in a recognition result storage part 106 or the recognition result obtained by merging the recognition results in the recognition result storage part 105 and incomplete output unit recording part 111, and an external output device 108 which receives the recognition result outputted by the recognition result output part 107 and informs a user of the recognition result through display or voice output and so on.
|