Evaluation of face recognition system in heterogeneous environments (visible vs NIR)

Author

Goswami, Debaditya ; Chan, Chi Ho ; Windridge, David ; Kittler, Josef

Author_Institution

Centre for Vision Speech & Signal Process., Univ. of Surrey Guildford, Guildford, UK

fYear

2011

fDate

6-13 Nov. 2011

Firstpage

2160

Lastpage

2167

Abstract

Performing facial recognition between Near Infrared (NIR) and visible-light (VIS) images has been established as a common method of countering illumination variation problems in face recognition. In this paper we present a new database to enable the evaluation of cross-spectral face recognition. A series of preprocessing algorithms, followed by Local Binary Pattern Histogram (LBPH) representation and combinations with Linear Discriminant Analysis (LDA) are used for recognition. These experiments are conducted on both NIR→VIS and the less common VIS→NIR protocols, with permutations of uni-modal training sets. 12 individual baseline algorithms are presented. In addition, the best performing fusion approaches involving a subset of 12 algorithms are also described.

Keywords

face recognition; image fusion; infrared imaging; lighting; statistical analysis; cross-spectral face recognition; fusion approach; heterogeneous environment; illumination variation problem; linear discriminant analysis; local binary pattern histogram representation; near infrared image; preprocessing algorithm; visible-light image; Databases; Face; Face recognition; Feature extraction; Histograms; Protocols; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on

Conference_Location

Barcelona

Print_ISBN

978-1-4673-0062-9

Type

conf

DOI

10.1109/ICCVW.2011.6130515

Filename

6130515