Illuminant-Invariant Face Recognition Using High-Order Local Derivative Pattern

This article presents a method of DCT-based illuminant compensation to enhance the accuracy of face recognition under an illuminant change. The basis of the proposed method is that the illuminant is generally located in low-frequency components in the DCT domain. Therefore, the effect of the illuminant can be compensated by controlling the low-frequency components. Moreover, a directional high-order local derivative pattern is used to detect robust features in the case of face motion. Experiments confirm the performance of the proposed algorithm, which achieved up to 96% when tested using a standard database. (C) 2018 Society for Imaging Science and Technology