Robust multi-TAR of barycenter contour for multiple views shape matching and retrieval

In this paper, we present a one dimensional descriptor for the two dimensional object silhouettes associated with each level of barycenter contour for multiple views shape matching and retrieval. Firstly, the barycenter contour is applied onto the shape contour. Then the averaging multi-triangle area representation (AMTAR) at each level of barycenter contour is computed as the shape descriptor. Finally, to classify among the shapes, the normalized cross-correlation function is used. Our algorithm is implemented on database consisting of 560 affine distorted shapes, chosen from MPEG-7 contour shape database CE-1. The experimental results indicate that the proposed method is invariant to affine transformation, robustness to the noise, and achieves high retrieval performance.