摘要 |
PROBLEM TO BE SOLVED: To provide an image processor and an image processing program capable of accurately collating two images. SOLUTION: The image processor acquires a reference image and a search object image (Steps S1 and S2), divides the reference image into a plurality of meshes (Step S3), and extracts a feature amount from the reference image (Step S4). The image processor selects a corresponding mesh on the search object image, based on an adaptability of the feature amount and the matching degree of a displacement direction for each mesh of the reference image (Step S7). COPYRIGHT: (C)2008,JPO&INPIT
|