The Library
2.5D gait recognition using curvature based color gait energy image
Tools
Tang, Jin, Luo, Jian, Tjahjadi, Tardi and Liu, Lijue (2014) 2.5D gait recognition using curvature based color gait energy image. Journal of Computational Information Systems, Volume 10 (Number 11). pp. 4737-4746. doi:10.12733/jcis10407 ISSN 0887-4417 .
Research output not available from this repository.
Request-a-Copy directly from author or use local Library Get it For Me service.
Official URL: http://dx.doi.org/10.12733/jcis10407
Abstract
This paper proposes a method for modeling human body and extracting the gait features for identifying the human subject. To characterize the body effectively and reduce the dimensionality of the gait feature space, 2.5 dimensional data is mapped onto the 2-dimensional space by Gaussian curvature and mean curvature based color gait images (CCGI). By averaging the CCGIs of a gait cycle, a 2D curvature based color gait energy image (CCGEI) is obtained. Gait recognition is achieved via 2-dimensional DCT compression and 2-dimensional principal component analysis with CCGEI. Experimental results on an in-house database captured using the Microsoft Kinect camera shows better performance than the use of existing gait features.
Item Type: | Journal Article | ||||
---|---|---|---|---|---|
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > Engineering | ||||
Journal or Publication Title: | Journal of Computational Information Systems | ||||
Publisher: | International Association for Computer Information Systems | ||||
ISSN: | 0887-4417 | ||||
Official Date: | 1 June 2014 | ||||
Dates: |
|
||||
Volume: | Volume 10 | ||||
Number: | Number 11 | ||||
Page Range: | pp. 4737-4746 | ||||
DOI: | 10.12733/jcis10407 | ||||
Status: | Peer Reviewed | ||||
Publication Status: | Published | ||||
Access rights to Published version: | Restricted or Subscription Access | ||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |