Real-time Hand Gesture Recognition by Shape Context Based Matching and Cost Matrix

Abstract

How to recognize the shape gesture for new human-computer interface without controller required and bring entertainment, games industries and information appliances in new ways. In this paper, we would illustrate a real-time hand gesture recognition system by using shape context matching and cost matrix. The shape context is taken as a basis description for shape matching. It can be regarded as a global characterization descriptor to represent the distribution of points in a set with scale and rotation invariance. In this paper, we developed a perceptual interface for human-computer-interaction based on real-time hand gesture recognition. User could interact with computer program by performing body gesture instead of physical contact. The image of hand gesture was captured from CCD. The hand gesture image was transformed into proper instruction according to the shape information respectively. The instruction was transferred to an appropriate program to execute. The experience of our preliminary results shown the precision rates was up to 70% ~ 90%.