Kernel fusion of multiple histogram descriptors for robust face recognition

Chan, Chi-Ho, Kittler, Josef and Tahir, Muhammad (2010) Kernel fusion of multiple histogram descriptors for robust face recognition. In: Structural, Syntactic, and Statistical Pattern Recognition. Lecture Notes in Computer Science, 6218 . Springer, pp. 718-727. ISBN 978-3-642-14979-5

Full text not available from this repository. (Request a copy)

Abstract

A multiple kernel fusion method combining two multiresolution histogram face descriptors is proposed to create a powerful representation method for face recognition. The multi resolution histogram descriptors are based on local binary patterns and local phase coding to achieve invariance to various types of image degradation. The multi-kernel fusion is based on the computationally efficient spectral regression KDA. The proposed face recognition method is evaluated on FRGC 2.0 database yielding very impressive results.

Item Type:	Book Section
Uncontrolled Keywords:	Local binary pattern, local phase quantization, kernel, fusion, linear discriminant analysis
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Sarah Howells
Date Deposited:	12 Sep 2012 13:54
Last Modified:	12 Oct 2019 22:26
URI:	http://nrl.northumbria.ac.uk/id/eprint/8794

Downloads