This paper presents a novel method for image classification. It differs from previous approaches by computing image similarity based on region matching. Firstly, the images to be classified are segmented into regions or partitioned into regular blocks. Next, low-level features are extracted from each segment or block, and the similarity between two images is computed as the cost of a pairwise matching of regions according to their related features. Experiments are performed to verify that the proposed approach improves the quality of image classification. In addition, unsupervised clustering results are presented to verify the efficacy of this image similarity measure.