A Novel Method for Dynamic Gesture Recognition

In this paper, we propose an automatic system that recognizes both continuous gestures and isolated in real-time, including Arabic numbers (0-9), alphabets (A-Z). We present a new method to get skin-color segmentation based on mixing nonlinear YCbCr elliptic cluster skill-color model and HSI skin-color segmentation model; then an improved HMM-FNN model is proposed for gesture recognition. The algorithm we present have the best performance and achieves average rate recognition 95.76% and 93.64% for Arabic Numbers and Alphabets, respectively.