| 摘要 |
<P>PROBLEM TO BE SOLVED: To improve precision for specifying a position of a collation area for extracting a feature quantity of a random pattern from a document to be collated, thereby reducing a collation time. <P>SOLUTION: A reading section 24 reads a document image of the document and a random pattern of a sheet as read data, a reference image is read out from registered data of an original stored in a storage section 32 for each original, and image matching is performed by comparing the read out reference image with the read data. If match is made, positional information indicating the position of the collation area determined based on a reference position set in the reference image as the reference is read out from the storage section 32, and the position of the collation area 34 is specified. The feature quantity of the random pattern is extracted from the specified area, and is collated with the feature quantity of the registered data of the original. <P>COPYRIGHT: (C)2009,JPO&INPIT |
