| 摘要 |
PROBLEM TO BE SOLVED: To automatically divide a document into plural pages by selecting a specific area on stored image data of pages and performing an OCR process for all the pages, comparing recognition results stored in a recognition result character string with a comparison pattern character string, and dividing the object document into plural pages when they match each other. SOLUTION: The document consisting of the pages is all read in at a time through an image scanner 24 and stored together in an external storage device 23, image data of an arbitrary page are read out to a RAM 22 and displayed at a display part 25, and a desired area to be recognized by OCR is selected. Then all the pages of the specified area are recognized by OCR and recognition result character strings are stored by the pages in the RAM 22; and the recognition result characters of the respective pages are compared with comparison pattern character strings stored in the RAM 22 and matching page numbers are stored. Image data of the document file stored in the external storage device 23 are read in the RAM 22, page by page, and image data having a stored matching page number are read in as one document and divided. |
