Scalable Approach for Content-Based Image Retrieval in Peer-to-Peer Networks

Peer-to-peer networking offers a modular solution for sharing visual data across the network. it is a demand issue to perform CBIR in peer-to-peer networks. While most of the existing methods focus on LSH visual features and have limitations of flexibility. In proposed system we use an innovative approach that is a p2p network with CBIR by employing the BOVW model. As images are scattered across the p2p network, which makes a static codebook less effective for retrieval tasks. here we propose a codebook updating method by sharpen the mutual information between the follow –up codebook, and the workload balance among peers that manage different code words. In order to further improve retrieval performance and reduce network cost.