Research On Static Hand Gesture Recognition Algorithm In Gesture Recognition Engine System

Human-computer interaction has become an important part of modern life, with the development of computer technology, people propose higher demand about the way of human-computer interaction, which accord with human interaction habits of human-computer interaction such as including voice recognition, gesture recognition, and other fields of research get more and more people's attention. Natural gestures provide a convenient means for communication of people, people can use the shape of the hand and the movement of the hand and the track of changes and other information to express some complex feelings and significance. Therefore, the research of human computer interaction system based on gesture recognition has theoretical significance, but also has practical application value.We discuss the basic process and algorithm of static hand gesture recognition in human-computer interaction engine system. Gesture segmentation algorithm based on face color sample the Gaussian model of YCbCr color space with motion template is proposed to solve gesture segmentation problem in complex background, which making the gesture segmentation accuracy has been greatly improved, lay the foundation for the realization of subsequent gesture recognition algorithm. The fusion feature of Hog and Hu moments as feature extraction of gesture image, effectively improve the robustness of gesture extraction algorithm. Principal component analysis method is used to reduce the dimensionality of feature vector, which solve the problem of excessive calculation caused by high dimension. We use SVM to classify the palm, fist, thumb and index finger, four static hand gesture. Through experiments. The results show that the algorithm has higher gesture recognition rate and stability.Based on the research of the human body static gesture recognition algorithm, an efficient and stable static gesture recognition algorithm is implemented, and the algorithm is applied to the gesture recognition engine system. The system can real-time recognize human hand gestures,and recognition of gesture is interpreted as computer can be understand mouse or keyboard events, achieve the control of Tetris game, so as to realized human-computer interaction...