Abstract: In this paper, a novel graph-based shape matching scheme for three-dimensional articulated objects is introduced. The underlying graph structure of a given 3D model is composed of its topological skeleton and local geometric features. Matching two graph structures is generally an NP-hard combinatorial optimization problem. To reduce computation cost, two graphs are embedded on a high-dimensional space, and then matched based on an extension of Earth Mover's Distance (EMD). Furthermore, the symmetric components of an articulated object are determined by a voting algorithm with a self-matching strategy to refine the matching correspondences. Experimental results show that the proposed approach is robust, even when the models are under the surface disturbances of noise addition, smoothing, simplification, similarity transformation, and pose deformation. In addition, the proposed approach is capable of handling both global and partial shape matching.