Multiblock-fusion scheme for face recognition

Publikationstyp
Conference Paper
Date Issued
2004-12-17
Sprache
English
Author(s)
Zhao, Shuyan  
Grigat, Rolf-Rainer  
Institut
Bildverarbeitungssysteme E-2  
TORE-URI
http://hdl.handle.net/11420/10087
First published in
Proceedings of the International Conference on Pattern Recognition  
Number in series
1
Start Page
309
End Page
312
Citation
Proceedings - International Conference on Pattern Recognition 1: 309-312 (2004-12-17)
Contribution to Conference
17th International Conference on Pattern Recognition (ICPR 2004)  
Publisher DOI
10.1109/ICPR.2004.1334114
Scopus ID
2-s2.0-10044237572
Publisher
IEEE
A multiblock-fusion scheme for face recognition is proposed in this paper. Three face recognition algorithms, i.e. probabilistic match, Linear Discriminant Analysis (LDA) and Discrete Cosine Transform (DCT) are compared under the fusion strategy. By combining global and local features, the multiblock-fusion enhances the robustness against variations of illumination, facial expressions and pose. Different partitions and combinations show specific performance for each method. The experimental results demonstrate that the fusion outperforms the single method. Some other characteristics of the three methods are also verified by the experiments.
DDC Class
004: Informatik
600: Technik