Title
An Illumination Insensitive Representation for Face Verification in the Frequency Domain
Abstract
We present a comparison of several face representation methods from the point of view of their sensitivity to illumination changes. The sensitivity is measured in terms of the overlap of the distributions of normalized correlations used for inter class and intra class image comparisons. The result suggests, that better illumination invariance could be achieved in feature spaces in the frequency domain derived for a differentiated image rather than using the original input image.
Year
DOI
Venue
2006
10.1109/ICPR.2006.249
ICPR (1)
Keywords
Field
DocType
inter class,illumination insensitive representation,frequency domain,better illumination invariance,intra class image comparison,face representation method,face verification,original input image,normalized correlation,differentiated image,feature space,face recognition,frequency domain analysis,feature extraction
Face verification,Frequency domain,Facial recognition system,Computer vision,Feature vector,Normalization (statistics),Pattern recognition,Invariant (physics),Computer science,Image matching,Feature extraction,Artificial intelligence
Conference
ISSN
ISBN
Citations 
1051-4651
0-7695-2521-0
4
PageRank 
References 
Authors
0.47
7
4
Name
Order
Citations
PageRank
Eduardo Garea Llano1236.42
Heydi Mendez Vazquez2917.10
J. Kittler3143461465.03
Kieron Messer448838.77