Publication of the week:

DR HARIN SELLAHEWA & PROFESSOR SABAH JASSIM

Monday 19 January 2009

Harin Sellahewa & Sabah Jassim, "Illumination and expression invariant face recognition: Toward sample quality-based adaptive fusion", Proceedings of the 2nd IEEE International Conference on Biometrics: Theory, Applications and Systems, 2008. ISBN: 978-1-4244-2729-1.

The performance of face recognition schemes is adversely affected as a result of significant to moderate variation in illumination, pose and facial expressions. Most existing approaches to face recognition tend to deal with one of these problems by controlling the other conditions. Beside strong efficiency requirements, face recognition systems on constrained mobile devices and PDAs are expected to be robust against all variations in recording conditions that arise naturally as a result of the way such devices are used. Wavelet-based face recognition schemes have been shown to meet well the efficiency requirements. Wavelet transforms decomposed face images into different frequency subbands at different scales, each giving rise to different representation of the face, and thereby providing the ingredients for a multi-stream approach to face recognition which stands a real chance of achieving an acceptable level of robustness. This paper is concerned with the best fusion strategy for a multi-stream face recognition scheme. By investigating the robustness of different wavelet subbands against variation in lighting conditions and expressions, we demonstrate the shortcomings of current non-adaptive fusion strategies and argue for the need to develop an image quality-based, intelligent, dynamic fusion strategy.

Abstracts of all the conference papers are available from the IEEE Explore website (external link).

Harin Sellahewa has a PhD from the University of Buckingham and teaches in the Department of Applied Computing. Sabah Jassim is Professor of Mathematics and Head of the Department of Applied Computing at Buckingham. Dr Sellahewa would like to acknowledge the contribution of the Dennison Research Grant 2008-09 (University of Buckingham).