全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

一种新的基于区域特征的快速步态识别方法

DOI: 10.11834/jig.200609212

Keywords: 步态识别,区域面积,N-best分类器

Full-Text   Cite this paper   Add to My Lib

Abstract:

步态是生物特征识别领域的一个新兴热点,它有以下3大优势:远距离识别、非侵犯性和难于隐藏。由于当前提出的大量步态特征提取算法要么过于复杂,要么识别率不高,难以满足自动步态识别的需要,因此,为了进行准确快速的步态识别,提出了一种新的基于区域特征的快速步态识别方法。该方法首先将检测出的2维人体侧影分为头部、躯干和腿部3个区域;然后分别提取每个区域的目标面积;最后将这些面积特征和人体的宽高比特征一起构成步态特征矢量用于训练和识别。此外,还改进了一种新的N―best分类器,该分类器在一定程度上提高了算法的识别率。实验结果表明,该新方法不仅简单快速,而且在UCSD和CMU数据集上分别得到了90%和98%左右的高识别率。

References

[1]  Kale A,Rajagopalan A,Cuntoor N,et al.Gait based recognition of humans using continuous HMMs[A].In:Proceedings of the International Conference on Face and Gesture Recognition[C],Washinton D C,USA,2002:321~326.
[2]  Huang P,Harris C,Nixon M.Recognising humans by gait via parametric canonical space[J].Journal of Artificial Intelligence in Engineering,1999,13(4):359~366.
[3]  Cunado D,Nixon M,Carter J.Using gait as a biometric via phase-weighted magnitude spectra[A].In:Proceedings of International Conference on Audio-and Video-based Biometric Person Authentication[C],Crans Montana,Switzerland,1997:95~102.
[4]  Ning Hua-zhong,Tan Tie-niu,Wang Liang,et al.Kinematics-based tracking of human walking in monocular video sequences[J].Image and Vision Computing,2004,22(5):429~441.
[5]  Zhang Rong,Vogler C,Metaxas D.Human gait recognition[J].Computer Vision and Pattern Recognition,2004,27(02):18~20.
[6]  Shutler J,Nixon M.Zernike velocity moments for description and recognition of moving shapes[A].In:Proceedings of British Machine Vision Conference(BMVC)[C],Manchester,UK,2001:705~714.
[7]  Wang Liang,Ning Hua-zhong,Hu Wei-ming.Gait recognition based on procrustes shape analysis[A].In:Proceedings of International Conference on Image Processing(ICIP)[C],Rochester,New York,USA,2002:22~25.
[8]  Wang Liang,Hu Wei-ming,Tan Tie-niu.Gait-based human identification[J].Chinese Journal of Computers,2003,26(3):353~360.[王亮,胡卫明,谭铁牛.基于步态的身份识别.计算机学报,2003,26(3):353~360.]
[9]  James B,Nixon M,Cater J.Automatic gait recognition by symmetry analysis[J].Pattern Recognition Letters,2003,24(13):2175~2183.
[10]  Liu Zong-yi,Sarkar S.Simplest representation yet for gait recognition:averaged silhouette[A].In:Proceedings of the 17th International Conference on Pattern Recognition[C],Cambridge,UK,2004:211~214.
[11]  Zhao Rong-chun,et al.Digital image processing[M].Xi\'an:The Publishing Company of Northwestern Poly-technical University.[赵荣椿等.数字图像处理导论[M].西安:西北工业大学出版社,1995.]
[12]  Phillips J,Moon H,Rizvi S,et al.The FERET evaluation methodology for face recognition algorithms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(10):1090~1104.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133