ABSTRACT

This paper presents a new classification and search method of 3D object features views. This method is an application of algorithms: • Close+ for an object views classification purpose • Algorithm for extracting association rules in order to extract the characteristic view. We use the geometric descriptor of Zernike Moments to index 2D views of 3D object. The proposed method relies on a Bayesian probabilistic approach for search queries. The resulting outcome is presented by a collection of 120 3D models of the Princeton-based benchmark and then compared to those obtained from conventional methods.