基于Gabor相位谱和流型学习的步态识别方法

被引:6
作者
杨晓超 [1 ]
周越 [1 ]
署光 [1 ]
张田昊 [1 ,2 ]
机构
[1] 上海交通大学图像处理与模式识别研究所
[2] 香港理工大学电子计算系
关键词
步态识别; 合成步态能量图; Gabor相位谱; 保局影射;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
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.
引用
收藏
页码:753 / 757
页数:5
相关论文
共 15 条
[1]  
Face recognition using Laplacianfaces. X He,S Yan,Y Hu,P Niyogi,and H J Zhang. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2005
[2]  
Improved gait recognition by gait dynamics normalization. Zongyi Liu,and Sudeep Sarkar. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2006
[3]  
Identification ofhumans using gait. Kale A,Sundaresan A,Rajagopalan A N,et al. IEEE Transactions on Image Processing . 2004
[4]  
Human gait recognition by the fusion of motion and static spatio-temporal templates. T.H.W.Lam,R.S.T.Lee,D.Zhang. Pattern Recognition . 2007
[5]  
Marginal fisher analysis and itsvariants for human gait recognition and content-based imageretrieval. D Xu,S Yan,D Tao,et al. IEEE Transactions . 2007
[6]  
How Iris Recognition Works. Daugman J. IEEE Transaction on Circuits and Systems for Video Technology . 2004
[7]  
Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition. Liu C,Wechsler H. IEEE Transactions on Image Processing . 2002
[8]  
The human ID gait challenge problem: data sets, performance and analysis. Sarkar S,Phillips P Jonathon,Liu Z,et al. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2005
[9]  
"Statistical Feature Fusion for Gait-Based Human Recognition". J. Han,and B.Bhanu. Proc. IEEE Conf. Computer Vision and Pattern Recognition . 2004
[10]  
Individual recognition using gait image energy. Han,J,Bhanu,B. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2006