Illumination Insensitive Face Recognition Using Gradientfaces

Abstract

The performance of most existing face recognition methods is highly sensitive to illumination variation. It will be seriously degraded if the training/testing faces under variable lighting. Thus, illumination variation is one of the most significant factor affecting the performance of face recognition and has received much attention in recent years. In this paper we propose a novel method called gradientface for face recognition under varying illumination. When we rarely know the strength, direction or number of light sources. The proposed method has the ability to extract illumination insensitive measure, which is then used for face recognition. The merits of this method is that neither does it require any lighting assumption nor does it need any training images. Gradientface method reaches very high recognition rate of 98.96% in the test on yele B face database. Further more the experimental results on Yale database validate that gradient faces is also insensitive to image noise and object artifacts such as facia;l expression.