A more distinctive representation for 3D shape descriptors using principal component analysis

Many researchers have used the Heat Kernel Signature (or HKS) for characterizing points on non-rigid three-dimensional shapes and Classical Multidimensional Scaling (Classical MDS) method in object classification which we quote, in particular, the example of Jian Sun et al. (2009) [1]. However, in this paper, the main focuses on classification that we propose a concise and provably factorial method by invoking Principal Component Analysis (PCA) as a classifier to improve the scheme of 3D shape classification. To avoid losing or disordering information after extracting features from the mesh, PCA is used instead of the Classical MDS to discriminate-as much as possible-feature points for each 3D shape in several poses. To demonstrate the practical relevance of this scheme, we present, illustrate and compare several assessments of the two proposed methods for non-rigid three-dimensional shapes classification based on heat diffusion. Across a collection of shapes, our results analysis show that the proposed contribution outperforms the classification method without PCA.