Face Recognition with One Sample Image per Class
Shaokang Chen, Brian C. Lovell · Intelligent information systems · 2003
There are two main approaches for face recognition with variations in lighting conditions. One is to represent images with features that are insensitive to illumination in the first place. The other main approach is to construct a linear subspace for every class under the different lighting conditions. Both of these techniques are successfully applied to some extent in face recognition, but it is hard to extend them for recognition with variant facial expressions. It is observed that features insensitive to illumination are highly sensitive to expression variations, which result in face recognition with changes in both lighting conditions and expressions a difficult task. We propose a new method called Affine Principal Components Analysis in an attempt to solve both of these problems. This method extract features to construct a subspace for face representation and warps this space to achieve better class separation. The proposed technique is evaluated using face databases with both variable lighting and facial expressions. We achieve more than 90% accuracy for face recognition by using only one sample image per class.