Illumination invariant face detection using classifier fusion

Authors

Alister Cordiner, University of WollongongFollow
Philip Ogunbona, University of WollongongFollow
Wanqing Li, University of WollongongFollow

RIS ID

25639

Publication Details

Cordiner, A., Ogunbona, P. & Li, W. (2008). Illumination Invariant Face Detection Using Classifier Fusion. Pacific-Rim Conference on Multimedia (pp. 456-465). Germany: Springer-Verlag.

Abstract

An approach to the problem of illumination variations in face detection that uses classifier fusion is presented. Multiple face detectors are seperately trained for different illumination environments and their results are combined using a combination rule. To define the illumination environments, the training samples are clustered based on their illumination using unsupervised training. Different methods of clustering the samples and combining the outputs of the classifiers are examined. Experiments with the AR face database show that the proposed method achieves higher accuracy than the traditional monolithic face detection method.