DICTA2002: Digital Image Computing Techniques and Applications, 21--22 January 2002, Melbourne, Australia Robust Face Recognition Using Multiple Eye Positions

This paper describes a robust face recognition algorithm using multiple candidate eye positions to improve recognition. Face recognition systems consist of four major stages. They are face detection, eye detection, face normalisation and face recognition. Most recognition schemes (eg. PCA) assume accurate knowledge of eye positions. By using multiple candidate eye positions, inaccuracies in eye detection can be overcome. An application of this method is given for a scheme with orthogonal complement PCA (OCPCA) features, and training and test image sets chosen from different databases. Experiments on face recognition have shown that about 5.4% performance improvement has been achieved by using multiple eye positions. 1