Region-based image retrieval using edgeflow segmentation and region adjacency graph

Traditional region-based image retrieval systems use only the dominant features within each region and ignore the useful relationship of neighboring regions. In this study, an integrated color/texture RBIR system using the region relationship is purposed. An image is first processed with the edgeflow technique to divide the image into several regions and to extract the important texture information. Then, the region adjacency graph is used to represent the regions and their spatial relationships in the segmented image. Furthermore, the image retrieval problem is reduced to a subgraph isomorphism algorithm, which is performed to verify the similarity between two graphs by a subgraph isomorphism heuristic algorithm. In experiments, several query results from the test database are used to evaluate the performance of the proposed system.