Illumination compensation method for local matching Gabor face classifier

Illumination compensation has proven to be crucial in face detection and face recognition. Several methods for illumination compensation have been developed and tested on the face recognition task using international available face databases. Among the methods with best results are the Discrete Cosine Transform (DCT), Local Normalization (LN) and Self-Quotient Image (SQI). Most of these methods have been applied with great success in face recognition using a principal component classifier (PCA). In the past few years, Local Matching Gabor (LMG) classifiers have shown great success in face classification relative to other classifiers. In this work we optimize several illumination compensation methods using the LMG face classifier. We use genetic algorithms as the optimization tool. We test our results on the FERET international face database. Results show that face recognition can be significantly improved by illumination compensation methods. The best results are obtained with the optimized LN method which yields a 31% reduction in the total number of errors in the FERET database.