Reconfigurable content-based image retrieval on peer-to-peer networks

Abstract

Performing content–based image retrieval (CBIR) from Internet scale databases connected through peer–to–peer (P2P) networks, abbreviated as P2P–CBIR, helps to explore the large–scale image database distributed over connected peers. For P2P topology, the flexible decentralised unstructured P2P network topology is adopted, based on which informed–like searching approach enables flexible routing control when peers join/leave. The scalable retrieval control can be developed based on the P2P–CBIR framework, which can adapt the query scope and progressively refine the accuracy during the retrieval process. By reconfiguring system at each regular interval times, we can effectively reduce trivial peer routing and retrieval operations due to imprecise configurations. Experiments demonstrated that the average recall rate of the proposed P2P–CBIR method with reconfiguration is higher than that without about 10.73%, while the latter outperforms previous methods, i.e., firework query model (FQM) and breadth–first search (BFS), about 27% and 57%, respectively, under the same time–to–live (TTL) setting.