Vision based gesture recognition system with single camera

In the field of virtual reality and interactive graphics, communication between human and computer becomes more and more important. This paper describes a real-time system for human-computer interaction through gesture recognition and hand tracking. Stable detection can be achieved by extracting two kinds of features: statistic-based feature and contour-based feature. Unlike most of previous works, our system recognizes hand gesture with just one camera, thus avoids the problem of matching image features between different views. This system can serve as a natural and convenient user input device, replacing mouse and trackball. Some of the applications that can demonstrate the benefits of the system will be given at the end of this paper.