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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Illumination compensation method for local matching Gabor face classifier


    Contributors:
    Perez, C A (author) / Castillo, L E (author) / Cament, L A (author)


    Publication date :

    2010-10-01


    Size :

    664640 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Gabor Feature Classifier for Face Recognition

    Liu, C. / Wechsler, H. / IEEE | British Library Conference Proceedings | 2001


    A Gabor feature classifier for face recognition

    Chengjun Liu, / Wechsler, H. | IEEE | 2001


    Shadow compensation and illumination normalization of face image

    Wang, H. | British Library Online Contents | 2013


    Classifier Vote and Gabor Filter Banks for Wafer Segmentation

    Bourgeat, P. / Meriaudeaua, F. | British Library Conference Proceedings | 2005


    Classifier vote and Gabor filter banks for wafer segmentation

    Bourgeat, P. / Meriaudeau, F. | IEEE | 2005