Hand Gesture Recognition Based On Tangent Distance

Hand gesture is a kind of natural and direct mode of communication in everyday life.With the development of computer technology,human becomes the more and more central part in human-computer interaction,so the research on hand gesture recognition becomes a foucs in this field. The research of hand gesture recognition has a wide range of applications such as:the aided communication between the deaf and the normal,the aided recognition of voice recognition,the control of VR,and the study of robot.The research of hand gesture recognition includes the following subjects: Education,Computer Graphology,Robot Motion and Physic etc.So it is a very meaningful subject.There are two methods on hand gesture recognition,recognition based on data glove and recogniton based on vision.Take hand as the input equipment directly,communication between human and computer will need no more other intermediate media.Users can control the machines around simply sign to it with the hand gesture user itself defines.However,gesture has the characters of multi-mode, multi-meaning and has discrepancy under certain time and space situation;moreover,human hands are complicated transformed objects and there is visual instability,all of which make gesture recognition based on sight become a challengeable multi-subject research goal.Hand gestures include static hand gestures,in which the shape of hand gestures is used to express the meaning,and dynamic hand gestures whose meanings are based on the track of the motion of hands. This paper performs study on static hand gestures recognition.A hand gestures recognition algortithm is presented based on the features of hand gestures.Hand gestures are recognized by global template matching.Tangent distance is presented to measure the similarity between test samples and template, eliminating sensitivity to sight and ensuring the invariance of different affine transformations such as translation,rotation,scaling and so on.We choose china sign language as the recognition object.At first, we take photos of different hand gesture and form small images collection of sign language.Then these images are preprocessed by image gray transforming,image smoothing and single threshold segmentation,and then the binary hand gesture images are formed for the next training and recognition. In the part of training,k-means clustering algorithm is used for performing the binary hand gesture images so as to get the hand gesture template.At last,hand gestures are recognized by template matching based on tangent distance on test samples.The experiments show our method is feasible for static hand gestures recognition and markedly improves recognition rate.