HAND POSTURE RECOGNITION BASED ON SVM USING ON MOBILE PHONE

In this paper, we present a novel method of hand posture recognition using on telephone. In this algorithm, we first detect the hand areas by used YCbCr skin-color likelihood algorithm. It is based the nature of skin color clustering in the distribution of CbCr and the maximum likelihood principle. Secondly we correct 300 hundred hand posture pictures which are transform to gray level to training the system by using Support Vector Machines (SVM) algorithm. And we will get the characteristic vectors of hand postures which are saved in hand-gesture.xml file. Thirdly we use the characteristic vectors compare with the detected hand areas by SVM to recognize hand postures. Finally we carried out a simulation experiment on a Windows XP system to evaluate the efficiency of the proposed algorithm. It can be seen from the experimentation that the system can achieve good recognition results.