Gait recognition based on Fourier descriptors

Gait recognition refers to automatic identification of an individual based on his/her style of walking; it is a new biometrics recognition technology. This paper attempts to describe a gait contour by using Fourier descriptors, to make a periodical analysis on the height and width ratio of the gait image, and to solve the problems resulting from an image sequence of different gait cycles by using dynamic time warping. By utilizing the presented algorithm, experiments made on the CMU data bank have achieved a comparatively high correct identification ratio.