Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (16): 168-170.

• 图形、图像、模式识别 • Previous Articles     Next Articles

Gait recognition based on combined features

JIANG Jia-fu,SONG Yi,YANG Ding-qiang   

  1. Department of Computer & Communication Engineering,Changsha University of Science and Technology,Changsha 410076,China
  • Received:2007-09-10 Revised:2008-01-02 Online:2008-06-01 Published:2008-06-01
  • Contact: JIANG Jia-fu

基于组合特征的步态识别

蒋加伏,宋 艺,杨鼎强   

  1. 长沙理工大学 计算机与通信工程学院,长沙 410076
  • 通讯作者: 蒋加伏

Abstract: Gait recognition is a new technique of recognition based on biologic character.In this paper,a new fusion algorithm is suggested wherein the static and dynamic features are fused to obtain optimal performance.The new fusion algorithm divides decision situations into two categories.The wavelet moment is used to describe the static features of gait sequence images,and the three widths of the body contour is used to describe the dynamic features.In addition,the Principal Component Analysis (PCA) for feature transformation of spatial templates is proposed.The experimental results demonstrate that the proposed algorithm performs an encouraging recognition rate.

Key words: gait recognition, wavelet moment, Principal Component Analysis(PCA)

摘要: 基于步态的身份识别是近几年出现的一种新的生物识别技术。提出了一种融合静态特征与动态特征的步态识别方法,该算法使用小波矩描述步态序列图像的静态特征,接着使用主元分析法对小波矩进行降维,而图像的动态特征则用人体轮廓的3个宽度特征来描述。最后,通过实验证明了该算法的有效性。

关键词: 步态识别, 小波矩, 主元分析法