基于Gabor相位谱和流型学习的步态识别方法  

Manifold Learning Based Gait Recognition Using Gabor Phase Spectrum

作　　者：杨晓超[1] 周越[1] 署光 张田昊[1,2] 

机构地区：[1]上海交通大学图像处理与模式识别研究所,上海200240 [2]香港理工大学电子计算系,中国香港九龙

出　　处：《电子学报》2009年第4期753-757,共5页Acta Electronica Sinica

基　　金：国家自然科学基金(No.60772097)

摘　　要：提出了一种有效的基于步态能量图像的身份识别方法.首先生成合成步态能量图像(GEI)丰富训练集样本数量.然后利用在以前文献中被忽略的具有良好识别性能的Gabor相位信息作为身份特征,并采用流型学习算法保局影射(LPP)将此高维数据在低维空间表示.通过使用简单的分类策略在USF步态数据库上进行对比实验,结果表明本方法的正确识别率优于现有其他的自动步态识别算法.This paper describes an effective gait recognition approach based on Gait Energy Image （GEI） representation. Synthetic GEI samples are first created to address the problem of lacking training data. Then the Gabor phase spectrum of GEI which was ignored in the previous works is utilized as the input feature, and it is subsequently projected into a low-dimensional space by using manifold learning algorithm Locality Preserving Projection. The proposed method is tested on the USF HumanID Database. The results show that our approach outperforms other state of the art automatic algorithms in terms of recognition accuracy.

关 键 词：步态识别 合成步态能量图 Gabor相位谱 保局影射 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]