Abstract
This paper presents a novel and efficient method for locat- ing deformable shapes in cluttered scenes. The shapes to be detected may undergo arbitrary translational and rotational changes, and they can be non-rigidly deformed, occluded and corrupted by clutters. All these problems make the accurate and robust shape matching very dif- ficult. By using a new shape representation, which involves a powerful feature descriptor, the proposed method can overcome the above difficul- ties successfully, and it possesses the property of global optimality. The experiments on both synthetic and real data validated that the proposed algorithm is robust to various types of disturbances. It can robustly de- tect the desired shapes in complex and highly cluttered scenes.