Real-time hand gesture recognition

This paper proposes a new  method of hand gesture recognition using Microsoft’s Kinect in real-time. Our system includes detecting and recognizing hand gestures via combining shape, local auto-correlation information and multi-class support vector machine (SVM). Our evaluation shows that the system recognizes one-handed gestures with more than 93% accuracy in real-time. The efficiency of the system execution is good enough and we are encouraged to develop a natural human-machine interaction in the near future.