Decision fusion for patch-based face recognition

Topçu, Berkay and Erdoğan, Hakan (2010) Decision fusion for patch-based face recognition. In: 20th International Conference on Pattern Recognition (ICPR 2010), Istanbul, Turkey

[thumbnail of topcu10dff.pdf] PDF
topcu10dff.pdf

Download (193kB)

Abstract

Patch-based face recognition is a recent method which uses the idea of analyzing face images locally, in order to reduce the effects of illumination changes and partial occlusions. Feature fusion and decision fusion are two distinct ways to make use of the extracted local features. Apart from the well-known decision fusion methods, a novel approach for calculating weights for the weighted sum rule is proposed in this paper. Improvements in recognition accuracies are shown and superiority of decision fusion over feature fusion is advocated. In the challenging AR database, we obtain significantly better results using decision fusion as compared to conventional methods and feature fusion methods by using validation accuracy weighting scheme and nearest-neighbor discriminant analysis dimension reduction method.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: decision fusion , face recognition , linear combiner training , patch-based face recognition
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Q Science > QA Mathematics > QA075 Electronic computers. Computer science
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Electronics
Faculty of Engineering and Natural Sciences
Depositing User: Hakan Erdoğan
Date Deposited: 10 Dec 2010 14:51
Last Modified: 26 Apr 2022 08:59
URI: https://research.sabanciuniv.edu/id/eprint/15903

Actions (login required)

View Item
View Item