步态识别作为一种新的生物特征识别技术,通过人走路的姿势实现对个人身份的识别和认证.算法利用步态轮廓图像边界到重心的距离矢量对步态轮廓图像进行描述,采用步态图像的高宽比进行步态的准周期性分析.利用隐马尔可夫模型进行步态时变数据匹配识别.算法在CMU数据库上进行实验取得了较高的正确识别率.

Gait recognition refers to automatic identification of an individual based on his/her style of walking, which is a new biometrics recognition technology. This paper attempts to describe gait contour by using the distance between the contour centroid and the pixels on the edge, to make quasi-periodic analysis on height and width ratio of gait image, and to solve the problems resulting from image sequence of different gait cycle by HMM. By utilizing the algorithm in the paper, the experiments with CMU database have achieved comparatively high correction identification ratio.