An image processing device includes an intermediate processing section for appending identification data to each pixel, showing a kind of region to which each pixel belongs, based on multi-value image data of a plurality of input images entered from a scanner, and a matching data generating section for generating matching data of each pixel. A CPU classifies the kind of region to which each input image belongs based on the identification data of each pixel stored into an identification data memory by means of a connection processing section, and compares the matching data stored in a matching data memory after processed adequately depending on the kind of region. Then, the CPU extracts matching points of the input images and connects the binary image data of the input images using the extracted matching points as reference points. Consequently, a plurality of input images can be restored to a single image by being connected accurately whether the input images are picture, shadow, or picture images.