基于步态能量图和不变矩的身份识别算法  

Human Recognition Based on Gait Energy Image and Invariant Moments

作　　者：王利巧[1] 裴亚南[1] 

机构地区：[1]河南科技大学现代教育技术与信息中心,洛阳471003

出　　处：《计算机与数字工程》2009年第10期128-131,共4页Computer & Digital Engineering

摘　　要：分析步态能量图即具有作为静态的外观特征,又包含了识别的动力学有用信息,同时证明了步态能量图对噪声的不敏感性。文章提出了一种基于步态能量图和不变矩的身份识别算法,介绍了不变矩的基本理论以及Hu提出的七个不变矩,利用图像不变矩的平移、尺度和旋转不变特性,从原始的步态能量图中提取不变矩特征作为步态能量图的输入特征向量,运用不变矩的最小距离分类器的模式匹配进行步态特征分类。最后在CASIA步态数据库上对所提出的算法和其他新的步态识别方法相比较。实验结果表明,提出的算法是一种有效的步态识别方法。In this paper, a new gait energy image and invariant moments based gait recognition algorithm is presented. Gait energy image shape, as a static appearance feature also contains useful information for identification, and the paper testify that gait energy image is less sensitive to silhouette noise. Secondly, the basic theory of moment invariants and seven moment invariants which were proposed by Hu are introduced. Using the traits of invariant moments, such as shift, rotation and scale invariant, invariant moment is extracted from the original gait energy image as input features, and the invariant moments least-distance classifier is adopted to recognize subjects. Finally we compare the proposed based on gait energy image and invariant moments gait recognition approach with other new gait recognition approaches on CASIA Gait Database. Experimental results show that the proposed approach is valid and has encouraging recognition performance.

关 键 词：生物特征 身份识别 特征提取 步态能量图 不变矩 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]