UUM Repository | Universiti Utara Malaysian Institutional Repository
FAQs | Feedback | Search Tips | Sitemap

A new approach in solving illumination and facial expression problems for face recognition


Yee, Wan Wong and Kah, Phooi Seng and Li, Minn Ang (2009) A new approach in solving illumination and facial expression problems for face recognition. In: International Conference on Computing and Informatics 2009 (ICOCI09), 24-25 June 2009, Legend Hotel, Kuala Lumpur.

[img]
Preview
PDF
Download (151kB) | Preview

Abstract

In this paper, a novel dual optimal multiband features (DOMF) method is presented to increase the robustness of face recognition system to illumination and facial expression variations.The wavelet packet transform first decomposes image into low-, mid- and high-frequency subbands and the multiband feature fusion technique is incorporated to select the subbands that are invariant to illumination and expression variation separately.These subbands form the optimal feature sets.Parallel radial basis function neural networks are employed to classify these feature sets.The scores generated by the neural networks are combined by an adaptive fusion mechanism where the level of illumination variations of the testing image is estimated and the weights are assigned to the scores accordingly.The experimental results show that DOMF outperforms other algorithms and also achieves promising performance on illumination and facial expression variation conditions.

Item Type: Conference or Workshop Item (Paper)
Additional Information: ISBN 978-983--44150-2-0 Organized by: UUM College of Arts and Sciences,Universiti Utara Malaysia.
Uncontrolled Keywords: Face recognition, multiband features, wavelet packet transform, illumination variation, adaptive fusion, neural network
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: College of Arts and Sciences
Depositing User: Mrs. Norazmilah Yaakub
Date Deposited: 01 Apr 2015 03:14
Last Modified: 01 Apr 2015 03:14
URI: http://repo.uum.edu.my/id/eprint/13463

Actions (login required)

View Item View Item