The Use Of The Hausdorff Distance In The Gesture Recognition

Hand gesture is an important and natural human-to-human interface in daily life.Hand gesture recognition system is applied to HCI(Human Computer Interface) to realize direct and natural communication,which is the development trend and fundamental object of gesture recognition.lt involves several fields such as Pattern Recognition, Image Process,Psychology and Cognitive Science.Recognition of hand gestures is separated into three steps: pre-proeessing.feature extraction and recognition. In the part of pre-processing, firstly performs image sharpening by means of Roberts operator to outstand gesture contour ,and last we get the binary image of the hand gesture.In the part of feature extraction.we extract CG(center of gravity) and contour of gesture image in the way of edge detection based on 8-connected boundary tracking.And extract key point of gesture image,by calculating curve degree of it's contour. In the part of feature recognition.firstly locate the position of gesture in the image by CG.After that.we can recognize the gesture by mean of Hausdorff distance(HD),depending on the set of key point.The experiment result proves that hand gesture recognition algorithm based on key points of gesture image is very efficient. And the recognition ratio is proved 85% accuracy.