Abstract:In this paper we propose a bayesian approach for near-duplicate image detection, and investigate how different probabilistic models affect the performance obtained. The task of identifying an image whose metadata are missing is often demanded for a myriad of applications: metadata retrieval in cultural institutions, detection of copyright violations, investigation of latent cross-links in archives and libraries, duplicate elimination in storage management, etc. The majority of current solutions are based either on voting algorithms, which are very precise, but expensive; either on the use of visual dictionaries, which are efficient, but less precise. Our approach, uses local descriptors in a novel way, which by a careful application of decision theory, allows a very fine control of the compromise between precision and efficiency. In addition, the method attains a great compromise between those two axes, with more than 99% accuracy with less than 10 database operations.