3D Object Retrieval Using a Global-Partial Analogy and the Bayesian Approach

3D retrieval has become an important field for applications that require 3D databases. Several descriptors have been defined in the past, most of them are based on the global geometric signature of the 3D objects and only a few of them allow a partial matching using segments of a 3D object as queries. In this paper, we propose to improve the results of global indexing by combining the partial signatures of the segments of a 3D object and its global descriptor using the Bayesian framework. The proposed approach improves significantly the results of global indexing and allows the retrieval of similar objects with different poses.