An efficient method for 3D objects retrieval based on fixed number of 2D views approach

In this paper an efficient method for 3D objects indexing and retrieval is presented. It is based on a set of six 2D views extracting using the projection box after a scale and pose normalization of the 3D models using PCA. Afterwards, we binarize each 2D view associated with the 3D object and we extract its external contour that represents its associated 2D shape. The Similarity among the 2D shapes is computed using our early proposed 2D shape descriptor based on multi-scale analysis. The experimental results illustrate the efficiency of our proposed method.