Comparing between data mining algorithms: "Close+, Apriori and CHARM" and “Kmeans classification algorithm” and applying them on 3D object indexing

Three-dimensional models are more and more used in applications in which the necessity to visualize realistic objects is felt (CAD/CAO, medical simulations, games, virtual reality etc.). Consequently, the management of large sizes of 3D data collections becomes an important field. The indexation of such data allows a designer for instance to easily find similar data - in a visual or semantic sense for a displayed requested object. There are two major approaches for 3d objects indexing; the search in the database can be done via requests that are either 3D objects or via some 2D views of the 3D object. In this contribution, we are interested in the latter. Our purpose is to extract characteristic views of 3D models using Data Mining algorithms "Apriori, Charm, Close+ and Extraction of association rules" and Zernike moments. Furthermore, the information retrieval relies on a Bayesian probabilistic approach. We present the obtained results using a database that contains 120 3D models selected from the Princeton Shape Benchmark, we associate to each 3D model 342 2D views then we compare them to the ones obtained with classical methods (e.g. Kmeans).