3D Object Retrieval Using 3D Packet Wavelet Transform and Knowledge Interpretation

In this paper a novel method for the efficient search and retrieval of 3D objects is presented. Firstly, the 3D PacketWavelet Transform is used to extract low-level descriptor vectors, which characterize geometrically a 3D object. Secondly, knowledge, in the sense of weight vectors, is formed and assigned to the low-level descriptor vectors. These two types of information are then combined and used into two sophisticated matching algorithms. Experiments were performed on a database of 3D objects so as to evaluate the proposed method in comparison with those most commonly cited in the literature. The experimental results show that the proposed method is superior in terms of precision versus recall and can be used for 3D model search and retrieval in a highly efficient manner.