A Supervised Shape Classification Technique Invariant under Rotation and Scaling

In this paper, we propose a new object classification technique based on polygonal approximation of the open profile of object. The ver- tices of polygonal approximation are formed by high curvature points of the profile and they are selected by Fourier transform of the object contour. A series of features are computed from the polygonal approximation and then the minimum distance classifier is used to recognize the object. The proposed technique is fast, simple and invariant under translation, rota- tion and scaling. Experimental results in recognition of static hand gestures show the performance of the proposed technique.