Human Gait Recognition: A Silhouette Based Approach

Abstract

Human gait has become an important biometric in recent years. A silhouette based method is suggested in this paper, to recognize human in video by their gait. We used averaged silhouette to represent the gait cycle. Principal Component Analysis has been used to reduce the dimensionality of the features. We applied Euclidean distance to measure the similarity of the averaged silhouettes. We implemented the algorithm on the TUM- IITKGP Gait Database which has been introduced recently. Although this method is sensitive to the appearance of the subject, it has low computational cost and it is simple. We implemented two experiments on the achieved averaged silhouettes. Our results illustrated that feature extracted from the averaged silhouettes which in them, the lower part of the body is eliminated are more suitable rather than those extracted from the complete averaged silhouettes. 