Paper Info
Title
Performance of correlation filters in facial recognition
Abstract
In this paper, we compare the performance of three composite correlation filters in facial recognition problem. We used the ORL (Olivetti Research Laboratory) facial image database to evaluate K-Law, MACE and ASEF filters performance. Simulations results demonstrate that K-Law nonlinear composite filters evidence the best performance in terms of recognition rate (RR) and, false acceptation rate (FAR). As a result, we observe that correlation filters are able to work well even when the facial image contains distortions such as rotation, partial occlusion and different illumination conditions.
Year
DOI
Venue
2011
10.1007/978-3-642-21587-2_17
MCPR
Keywords
Field
DocType
facial recognition problem,facial image database,false acceptation rate,composite correlation filter,recognition rate,facial image,k-law nonlinear composite filter,best performance,asef filters performance,correlation filter
Computer vision,Facial recognition system,Computer science,Correlation,Artificial intelligence,Image database
Conference
Citations 
PageRank 
References 
1
0.37
4
Authors
3
Name
Order
Citations
PageRank
Everardo Santiago-Ramirez161.47
J. A. Gonzalez-Fraga232.09
J. I. Ascencio-Lopez310.37