Abstract: The present invention provides an image matching method which allows non-ear image positional shifts to be corrected on a real time basis, and an economical product testing system using this method. A two dimensional test image, consisting of pixels arranged as a matrix of bits distributed in both the vertical direction and the horizontal scanning direction, and an associated reference image are subjected to template matching at a cell matching arithmetic unit for each of line blocks consisting of a plurality of scan lines. The result of the template matching are quantitatively evaluated at an evaluation unit as being good or bad, and positional shifts are sequentially computed according to good evaluation results. Based on the positional shifts thus obtained, the comparative pixel addresses are accordingly corrected before the two images are compared at the comparator.

Abstract: In appearance inspection for a printed image, image data without a fault or image data in which a fault is corrected is selected as a reference image, and a table having, as its elements, flags in a number corresponding to the number of levels of an image for each pixel of the reference image is prepared. An index space is formed by a set of tables of all the pixels, and a reference pattern is formed by turning on the flags in the space. The flags in the index space are inspected and determined once for each pixel in accordance with attribute values of an image to be inspected. Setting of an allowable range for inspection is performed as pre-processing before flag propagation processing for turning on flags within the allowable range in the index space is performed. The flag is not limited to a binary one having values of ON and OFF but may be a multivalue one. The index space can be compressed by expressing flags by a hierarchical structure utilizing image data characteristics.