Cross-channel histogram equalisation for colour face recognition

Authors:
Stephen King;Gui Yun Tian;David Taylor;Steve Ward
Affiliations:
The School of Computing & Engineering, University of Huddersfield, Queensgate, Huddersfield;The School of Computing & Engineering, University of Huddersfield, Queensgate, Huddersfield;The School of Computing & Engineering, University of Huddersfield, Queensgate, Huddersfield;The School of Computing & Engineering, University of Huddersfield, Queensgate, Huddersfield
Venue:
AVBPA'03 Proceedings of the 4th international conference on Audio- and video-based biometric person authentication
Year:
2003

Citing 5
Cited 0

Face recognition: the problem of compensating for changes in illumination direction

ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
Face and Gesture Recognition: Overview

IEEE Transactions on Pattern Analysis and Machine Intelligence
An Introduction to Digital Image Processing

An Introduction to Digital Image Processing
Face Recognition: Features Versus Templates

IEEE Transactions on Pattern Analysis and Machine Intelligence
Eigenfaces for recognition

Journal of Cognitive Neuroscience

Quantified Score

Hi-index	0.00

Visualization

Abstract

Changes in illumination conditions will alter the appearance of digital images that will in turn have a detrimental effect on face recognition. To overcome the problem, histogram equalisation has already been applied to grey world face recognition and extended to colour object recognition by independently processing the three colour channels. This paper furthers this work by introducing a new technique, cross-channel histogram equalisation, and reports upon its application to colour face recognition under different illumination conditions. Based on the experimental tests, our approach has been shown to outperform other efforts on histogram equalisation for normalisation. Finally we give our conclusions and discuss future work.