Volume 6 Number 7 (Jul. 2011)
Home > Archive > 2011 > Volume 6 Number 7 (Jul. 2011) >
JSW 2011 Vol.6(7): 1345-1352 ISSN: 1796-217X
doi: 10.4304/jsw.6.7.1345-1352

Manifold Learning Based Gait Feature Reduction and Recognition

Suyuan Wei1, Chao Ning2, Youxing Gong1
1Research Inst. Of Computer Peripheral, Xidian Univ., Xi’an, China Xi’an High Technology Inst., Xi’an, China
2Xi’an High Technology Inst., Xi’an, China

Abstract—The moving objectives’ images are in tensor format in reality. That using for reference the thought of tensor space dimension reduction to gain the optimal gait characters with low dimension inaugurate a new gait recognition way. A novel gait expression and recognition algorithm based on the tensor space is introduced here. It is a tensor space learning algorithm that could investigate the inherent geometrical structure of the data manifold. The within-class and the between-class similarity graphs are respectively defined so as to preserve the local structure of the manifold and the global data information. It improves the ability of gait data reconstructing and the recognizing efficiency. The optimization problem of finding the optimal tensor subspace is deduced to an iteratively computation problem about resolving the generalized eigenvectors. The optimal tensor is used to express the gait character and recognize the individual. And it reduced the gait character dimension, at the same time the storage and calculation cost were cut down. The experiments with the SOTON gait database demonstrated the validity of the proposed method. And the comparison among the tensor subspace analysis, the principal component analysis, the linear discriminate analysis and proposed method showed that the recognition performance of the our improved algorithm outperformed others.

Index Terms—gait character extraction, gait recognition, tensor space mapping, dimension reduction


Cite: Suyuan Wei, Chao Ning, Youxing Gong, "Manifold Learning Based Gait Feature Reduction and Recognition," Journal of Software vol. 6, no. 7, pp. 1345-1352, 2011.

General Information

ISSN: 1796-217X (Online)
Frequency:  Bimonthly (Since 2020)
Editor-in-Chief: Prof. Antanas Verikas
Executive Editor: Ms. Yoyo Y. Zhou
Abstracting/ Indexing: DBLP, EBSCO, Google Scholar, ProQuest, INSPEC(IET), ULRICH's Periodicals Directory, WorldCat, etc
E-mail: jsw@iap.org
  • Apr 26, 2021 News!

    Vol 14, No 4- Vol 14, No 12 has been indexed by IET-(Inspec)     [Click]

  • Jun 22, 2020 News!

    Papers published in JSW Vol 14, No 1- Vol 15 No 4 have been indexed by DBLP     [Click]

  • Sep 13, 2021 News!

    The papers published in Vol 16, No 6 have all received dois from Crossref    [Click]

  • Jan 28, 2021 News!

    [CFP] 2021 the annual meeting of JSW Editorial Board, ICCSM 2021, will be held in Rome, Italy, July 21-23, 2021   [Click]

  • Sep 13, 2021 News!

    Vol 16, No 6 has been published with online version     [Click]