The Research Of Gait Recognition Based On Area Of Regional

Gait recognition is an important form of biological feature recognition. Gait recognition is a complex and challenging topic in pattern recognition. Gait is the only biological characteristic that can be perceived in the case of long-distance. It has intrigued researchers in the field of visual monitoring of the potential applications. Currently, many scholars are engaging in gait recognition using a variety of methods. However,it is always a hot issue how to improve the recognition rate and how to reduce the complexity of computing in gait recognition. Based on above problems, we have studied the selection and identification of gait characteristics and proposed a new gait recognition method based on regional area characteristics.Firstly,we propose a gait recognition strategy that only use the following parts of the human hip joint., and calculates the width of the silhouette area to descrip the gait cycle, We analyze the action in walking changes, and clearly find that the upper part is almost unchanged in addition to arm in the course of people walking, the lower part of the hip changes regularly. Therefore, removing the upper part of hip, our studies not only can greatly reduce the computing complexity, but also improve the recognition effectly. it is very important to make a periodic analysis for the continuous change of the gait recognition. This article bases on the continuous change of gait in a walking sequence, calculates the width of the silhouette area, that is to calculate the number of pixels within the target area. So the selection of the key frame is the first step in gait recognition.Secondly , we only select the lower part of the hip as the research object .So far the best method of recognition is the gait contour changes. But it needs complex calculation for long time. Based on these, the small area of silhouette is choosen to replace contours, Then the extracted gait features are matched by the nearest neighbor distance criterion. It not only maintains a good recognition rate, but also reduces the computation. The experiment proved that the method is feasible.Finally, LDA and PCA combined is used to the gait recognition. Firstly,we use the PCA to gait image feature vector, then use Fisher criteria to select eigenvectors. Combine the two methods, using not only the characteristic of decorrelation, but also the classification property of Fisher criteria. Experiments show that this method increase recognition speed and higer recognition rate.