Affine Invariant Shape Recognition Based on Multi-Level of Barycenter Contour

In this paper, a new multiresolution created from multi-level of barycenter contour is proposed in order to reduce the moderate amount of noise and to improve the retrieval efficiency of the recognition task in computer vision. Then, the triangle area representation with two points (TAR-2p) signature at each level of barycenter contour is introduced as the shape representation. Finally, the normalized cross-correlation function at each level is used for measuring the similarity among the shapes. Our experiment has been performed on database consisting of 560 affine distorted shapes, chosen from MPEG-7 contour shape database CE-1. The results illustrate that our algorithm is invariant to affine transformation, robustness to the noise. Moreover, it achieves high retrieval efficiencies when compares to those of the Triangle Area Representation with three points (TAR-3p) signature and the centroid distance signature.