Abstract
This paper compares four methods of feature extraction: Fractional Eigenfaces and Vander Lugt Correlator as global methods, and Gabor Ordinal Measures and Uniform Local Binary Pattern as local ones. We evaluate the four methods on the standard FERET probe data sets in order to study the robustness of these techniques against illumination variation, facial expression variation and aging. The Gabor ordinal measures as a combination of Gabor filters and ordinal measures outperforms the others methods on the four test sets in terms of recognition rate.