Dynamic biometrics fusion at feature level for video-based human recognition

Wu, Qiang, Wang, Liang, Geng, Xin, Li, Ming and He, Xiangjiang 2007, Dynamic biometrics fusion at feature level for video-based human recognition, in IVCNZ 2007 : Proceedings of Image and Vision Computing New Zealand, Image and Vision Computing NZ, [Hamilton, N.Z.], pp. 152-157.

Attached Files
Name Description MIMEType Size Downloads

Title Dynamic biometrics fusion at feature level for video-based human recognition
Author(s) Wu, Qiang
Wang, Liang
Geng, Xin
Li, Ming
He, Xiangjiang
Conference name Image and Vision Computing New Zealand. Conference (2007: Hamilton, N.Z.)
Conference location Hamilton, N.Z.
Conference dates 5-7 December 2007
Title of proceedings IVCNZ 2007 : Proceedings of Image and Vision Computing New Zealand
Editor(s) Cree, Michael J.
Publication date 2007
Conference series Image and Vision Computing New Zealand Conference
Start page 152
End page 157
Publisher Image and Vision Computing NZ
Place of publication [Hamilton, N.Z.]
Keyword(s) human recognition
multimodal biometrics
dynamic fusion
Summary This paper proposes a novel human recognition method in video, which combines human face and gait traits
using a dynamic multi-modal biometrics fusion scheme. The Fisherface approach is adopted to extract face
features, while for gait features, Locality Preserving Projection (LPP) is used to achieve low-dimensional
manifold embedding of the temporal silhouette data derived from image sequences. Face and gait features are
fused dynamically at feature level based on a distance-driven fusion method. Encouraging experimental results
are achieved on the video sequences containing 20 people, which show that dynamically fused features produce
a more discriminating power than any individual biometric as well as integrated features built on common static
fusion schemes.
Notes Reproduced with the specific permission of the copyright owner.
ISBN 9780473130084
0473130084
Language eng
Field of Research 080104 Computer Vision
HERDC Research category E1 Full written paper - refereed
Copyright notice ©2007, Image and Vision Computing NZ
Persistent URL http://hdl.handle.net/10536/DRO/DU:30008097

Document type: Conference Paper
Collection: School of Engineering and Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Access Statistics: 457 Abstract Views, 59 File Downloads  -  Detailed Statistics
Created: Mon, 29 Sep 2008, 09:04:31 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.