Shape retrieval using triangle-area representation and dynamic space warping

We present a shape representation and a matching method for nonrigid shapes with closed contours. The representation utilizes the areas of the triangles formed by the boundary points to measure the convexity/concavity of each point at different scales (or triangle side lengths). This representation is effective in capturing both local and global characteristics of a shape, invariant to translation, rotation, and scaling, and robust against noise and moderate amounts of articulation and occlusion. In the matching stage, we employ a dynamic space warping (DSW) algorithm to search efficiently for the optimal (least cost) correspondence between the points of two shapes. Then, we derive a dissimilarity distance based on the optimal correspondence. We demonstrate the performance of our method using four standard tests on two well-known shape databases. The results show the superiority of our method over other recent methods in the literature.

• Type: Journal
• Year: 2007
• Where: PR
• Authors: Naif Alajlan, Ibrahim El Rube, Mohamed S. Kamel, George H. Freeman
• Keywords: Nonrigid Shapes, PR 2007, Shape Representation, Triangle