Improvement of illumination‐insensitive features for face recognition under complex illumination conditions

Abstract

Complex illumination condition is one of the most critical challenging problems for practical face recognition. In this study, the authors propose a novel method to improve the illumination invariants for solving this challenge. Firstly, a new method based on the Lambert reflectance model is proposed to extract illumination invariant, which is insensitive to complex illumination variations. Secondly, in order to repair the defects caused by the process of illumination invariants extraction, the fast mean filter is utilised to smooth and remove noise. Lastly, for raising the richness of information in the output image, a nonlinear normalisation transformation is proposed. Compared with the state-of-the-arts, experimental results show that the proposed method can extract more robust illumination invariants. Apart from it, the richness of information in the processed image is greater and the performance of the face recognition rate is superior.