A Fast Shape Context Matching Using Indexing

In this paper, an efficient 2D shape matching algorithm is proposed. The proposed algorithm uses the mean distances and standard deviations of shape contexts as the index of shapes to reduce the search space of the previous work on shape matching with shape context descriptor. The best-fit ellipse modeling is adopted as the preprocessing for normalizing its scale. The simulation databases include human body postures and shapes of 3D objects from MPEG-7 silhouettes, and the COIL data set, respectively. Experimental results show that the recognition rates are 98% for human body postures and 100% for shapes of 3D objects.