基于核二维主成分分析算法的步态识别

摘要

Gait recognition is a new biometric identification technology, it is the identity of the methods to identify people by the way they walk. In this paper, in order to carry on extraction and recognition of human gait characteristics more rapidly and effectively, a method is used based on the Kernel two Dimensional Principal Component Anal-yses(K2DPCA) to get the.gait feature extraction and Support Vector Machine(SVM) method to identify. The algorithm obtains the gait quasi-periodicity through analyzing the width information of the lower limbs' gait contour edge, and the GEI is calculated from gait period. The kernel two dimensional principal component analysis method is used to extract gait feature vector generated by the GEI, the' SVM classifier is adopted to distinguish the differences. Experimental results show that the method proposed in this paper is efficient.%步态识别是一种新的生物认证技术,它是通过人的行走方式来识别人类身份的方法.为了更加快速有效地对人体步态特征进行提取和识别,采用了基于核二维主成分分析(Kernel two Dimensional Principal Component Analyses,K2DPCA)的方法进行步态特征提取,运用支持向量机(SVM)进行步态识别.根据人体步态下肢摆动距离统计出步态周期,得到步态能量图(GEI),对生成的GEI采用核二维主成分分析方法进行步态特征向量提取,采用SVM分类器进行分类识别.实验结果表明该方法具有很好的识别效果.