An Intelligent Content-based Image Retrieval System based on Color, Shape and Spatial Relations

Content-based multimedia information retrieval is an interesting but difficult research. Current approaches include the use of color, texture, and shape information. In this paper, we present a hybrid approach, which incorporates color, shape and spatial relations among objects in a picture, to retrieve images from nearly 5000 pictures. A revised color scheme and its indexing technique are used to improve the efficiency of retrieval, according to our clustering method and color sensation. A seed filling like mechanism is used to extract shape and spatial relations among objects. Qualitative approach is applied to the similarity comparison of spatial differences. The system also implemented with a friendly GUI, which allows sketch images, as well as relevance feed back to improve the accuracy of retrieval. Our experience shows that the system is able to retrieve image information efficiently by the proposed approaches.