Illumination Normalization for Outdoor Face Recognition by Using Ayofa-filters

Abstract In this paper, we propose an illumination normalization approach, which apparently improves the face recognition accuracy in outdoor environments. The proposed approach computes the frequency variability and reflection direction on local face regions where the direction of the light source is unknown. It effectively recovers the illumination on a face surface. Majority of conventional approaches needs constant albedo coefficients as well as known illumination source direction to recover the illumination. Our novel approach computes unknown reflection directions by using spatial frequency components on salient regions of a face. The method requires only one single image taken under any arbitrary illumination condition where we do not know the light source direction, strength, or light sources. The method relies on the spatial frequencies and does not need to use any precompiled face model database. It references the nose tip to evaluate the reflection model that contains six different reflection vectors. We tested the proposed approach by still images from major face databases and conducted testing by using video images from an IP camera placed in outdoor. The efficiency of the Ayofa-filter was tested by both holistic-based approaches and feature-based methods. We used principal component analysis (PCA) and linear discriminant analysis (LDA) as holistic methods and used Gabor-wavelets and active appearance model (AAM) as feature-based methods. The error rates obtained after the illumination-normalization show that our novel method significantly improves the recognition ratio with these recognition methods.