Heterogeneous Face Recognition: Matching NIR to Visible Light Images

Matching near-infrared (NIR) face images to visible light (VIS) face images offers a robust approach to face recognition with unconstrained illumination. In this paper we propose a novel method of heterogeneous face recognition that uses a common feature-based representation for both NIR images as w...

Full description

Saved in:
Bibliographic Details
Published in2010 20th International Conference on Pattern Recognition pp. 1513 - 1516
Main Authors Klare, B, Jain, A K
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2010
Subjects
Artificial neural networks
Face
Face recognition
Feature extraction
feature-based
near infrared
Probes
random subspaces
spare representation
Testing
Training
Online AccessGet full text
ISBN1424475422
9781424475421
ISSN1051-4651
DOI10.1109/ICPR.2010.374

Cover

More Information
Summary:Matching near-infrared (NIR) face images to visible light (VIS) face images offers a robust approach to face recognition with unconstrained illumination. In this paper we propose a novel method of heterogeneous face recognition that uses a common feature-based representation for both NIR images as well as VIS images. Linear discriminant analysis is performed on a collection of random subspaces to learn discriminative projections. NIR and VIS images are matched (i) directly using the random subspace projections, and (ii) using sparse representation classification. Experimental results demonstrate the effectiveness of the proposed approach for matching NIR and VIS face images.
ISBN:1424475422
9781424475421
ISSN:1051-4651
DOI:10.1109/ICPR.2010.374