loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'99) - Volume 1
Improving Identification Performance by Integrating Evidence from Sequences
Fort Collins, Colorado
June 23-June 25
ISBN: 0-7695-0149-4
ASCII Text
x 
 
Gareth J. Edwards, Chris J. Taylor, Tim F. Cootes, "Improving Identification Performance by Integrating Evidence from Sequences," Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, vol. 1, pp. 1486, 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'99) - Volume 1, 1999.
 
 
BibTex
x
 
@article{ 10.1109/CVPR.1999.786982,
author = {Gareth J. Edwards and Chris J. Taylor and Tim F. Cootes},
title = {Improving Identification Performance by Integrating Evidence from Sequences},
journal ={Computer Vision and Pattern Recognition, IEEE Computer Society Conference on},
volume = {1},
year = {1999},
issn = {1063-6919},
pages = {1486},
doi = {http://doi.ieeecomputersociety.org/10.1109/CVPR.1999.786982},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
TI - Improving Identification Performance by Integrating Evidence from Sequences
SN - 1063-6919
SP
EP
A1 - Gareth J. Edwards,
A1 - Chris J. Taylor,
A1 - Tim F. Cootes,
PY - 1999
VL - 1
JA - Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
ER -
 
Gareth J. Edwards, University of Manchester
Chris J. Taylor, University of Manchester
Tim F. Cootes, University of Manchester
We present a quantitative evaluation of an algorithm for model-based face recognition. The algorithm actively learns how individual faces vary through video sequences, providing on-line suppression of confounding factors such as expression, lighting and pose. By actively decoupling sources of image variation, the algorithm provides a framework in which identity evidence can be integrated over a sequence. We demonstrate that face recognition can be considerably improved by the analysis of video sequences. The method presented is widely applicable in many multi-class interpretation problems.
Citation:
Gareth J. Edwards, Chris J. Taylor, Tim F. Cootes, "Improving Identification Performance by Integrating Evidence from Sequences," cvpr, vol. 1, pp.1486, 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'99) - Volume 1, 1999
Usage of this product signifies your acceptance of the Terms of Use.