RBIR using interest regions and binary signatures

Abstract. In this paper, we introduce an approach to overcome the low accuracy of the Content-Based Image Retrieval (CBIR) (when using the global features). To increase the accuracy, we use Harris-Laplace detector to identify the interest regions of an image. Then, we build the Region-Based Image Retrieval (RBIR). For the efficient image storage and retrieval, we encode images into binary signatures. The binary signature of an image is created from its interest regions. Furthermore, this paper also provides an algorithm for image retrieval on S-tree by comparing the images' signatures on a metric similar to EMD (earth mover's distance). Finally, we evaluate the created models on COREL's images.