The last decade has observed great curiosity in research on content-based image retrieval. This has covered the way for a large number of new techniques and systems, and a growing interest in associated fields to support such systems. Likewise, digital imagery has expanded its horizon in many directions, resulting in an explosion in the volume of image data required to be organized. Content-Based Image Retrieval (CBIR) in Peer to Peer system uses the visual contents of an image such as color, shape, texture, and spatial layout to represent and index the image. The distributed nature of these systems, where nodes are typically located across networks, innately hinders the efficient retrieval of information. we consider the searching and retrieval of information that is dispersed on peers of a network. Our approach builds on work in unstructured P2P systems and uses only local knowledge. The reason for using unstructured P2P systems is that ,they impose very small demands on individual nodes and can easily accommodate nodes of varying power Active research in CBIR is geared towards the development of methodologies for analyzing, interpreting cataloging and indexing image database. The quality of response is heavily dependent on the choice of the method used to generate feature vectors and similarity measure for comparison of features we proposed an algorithm which includes the advantages of various other algorithms to improve the accuracy and performance of retrieval. The accuracy of color histogram based matching can be increased by using Color lookup table (CLT) for successive refinemen .
Keywords : CBIR,P2P,CLT .