On view-invariant gait recognition: A feature selection solution

Ning Jia, Victor Sanchez, Chang Tsun Li

    Research output: Book chapter/Published conference paperConference paperpeer-review

    18 Citations (Scopus)
    8 Downloads (Pure)

    Abstract

    The authors present an improved feature selection solution for the view-invariant gait recognition problem, based on their previously proposed method called view-invariant feature selector (ViFS), which automatically reconstruct an optimised gallery template from a set of multi-view gallery templates. They improved ViFS by introducing a constraint to make sure that the reconstructed features have the same scale as the original features, thus reducing the number of misclassifications caused by data misalignment. They evaluate the improved ViFS on the CASIA B and OU-ISIR large population datasets by performing a wide range of comparative studies in order to explore and confirm its effectiveness. Evaluation results indicate that the proposed framework is very effective for view-invariant gait recognition tasks.
    Original languageEnglish
    Title of host publicationIET biometrics
    Subtitle of host publicationSpecial issue: Selected papers from the international workshop on biometrics and forensics (IWBF2017)
    EditorsMichael Fairhurst
    Place of PublicationUnited Kingdom
    PublisherInstitution of Engineering and Technology (IET)
    Pages287-295
    Number of pages9
    Volume7
    Edition4
    DOIs
    Publication statusPublished - 25 Jun 2018
    Event5th International Workshop on Biometrics and Forensics: IWBF 2017 - University of Warwick, Coventry, United Kingdom
    Duration: 04 Apr 201705 Apr 2017
    https://warwick.ac.uk/fac/sci/dcs/people/chang-tsun_li/iwbf2017/ (Conference website)

    Publication series

    NameIET Biometrics
    PublisherThe Institution of Engineering and Technology
    ISSN (Print)2047-4938

    Conference

    Conference5th International Workshop on Biometrics and Forensics
    Country/TerritoryUnited Kingdom
    CityCoventry
    Period04/04/1705/04/17
    OtherIWBF is an international forum devoted specifically to facilitate synergies in research and development in the areas of multimedia forensics, forensicbiometrics and forensic science. IWBF provides the meeting place for those concerned with the usage of multimedia analysis in forensic applications and biometric recognition systems, attracting participants from industry, research, academia and end-users.
    Internet address

    Fingerprint

    Dive into the research topics of 'On view-invariant gait recognition: A feature selection solution'. Together they form a unique fingerprint.

    Cite this