摘要 |
<P>PROBLEM TO BE SOLVED: To provide a document reader which improves operation efficiency in editing the content of an original document by automatically extracting, from among read images, a read image including written information which is written into the original document by a user. <P>SOLUTION: The document reader comprises: an optical reading unit which optically reads a plurality of documents and respectively generates read images; an image determination unit which subjects the read images to determination of whether colored written image is included; a character recognition unit which recognizes characters in the read image determined to include the written image by the image determination unit and generates document data made of character strings; and an image file generation unit which generates an image file composed of the read image including the written image and the document data obtained from the read image. <P>COPYRIGHT: (C)2012,JPO&INPIT |