Contour Based Hand Gesture Recognition Using Depth Data
Le Tran Nguyen, Cong Thanh, Tung Nguyen Ba, Cuong Ta Viet, Ha Le Thanh · 2013
This paper presents a contour based method for recognizing hand gesture using depth image data. In this research, a motion based algorithm is used to detect and track human hand. Then, the hand contours are extracted and described by rotationand scale-invariant feature vectors. Finally, a logistic regression classifier is employed for hand gesture recognition. For evaluating the real-time performance of this hand recognition method, a test-bed application is built. The experimental results exhibit the high recognition accuracy and efficiency of our approach.