Nuisance Attribute Projection in the Logarithm Domain for Face Recognition under Severe Illumination Changes

Illumination induced appearance changes represent one of the open challenges in automated face recognition systems still significantly influencing their performance. Several techniques have been presented in the literature to cope with this problem; however, a universal solution remains to be found. In this paper we present a novel normalization scheme based on the nuisance attribute projection (NAP), which tries to remove the effects of illumination by projecting away multiple dimensions of a low dimensional illumination subspace. The technique is assessed in identification experiments performed on the YaleB database, where an average rank one recognition rate of 99.6% is obtained on the test image sets. Comparative results with state-of-the-art techniques also show the competitiveness of the proposed technique.