Gait recognition based on two-dimensionality linear discriminant analysis

摘要

Gait recognition, as one of new fields in biometric recognition, has the particular capability to recognize people at a distance when other biometrics might not be perceivable, such as face and iris. Furthermore, it is difficult to disguise gait behavior without hampering progress, which is of particular interest in scene of crime analysis. It can be used as an unobtrusive biometric measure to identify people at a distance without any attention of the human subjects, which is better than some other biometric measure ways such as face, fingerprint, and iris. In this paper, a gait recognition method is proposed based on two-dimensionality linear discriminant analysis (2D-LDA). The experiments on the real gait image database demonstrate that 2D-LDA is effective and feasible for gait recognition.