Diagonal Symmetric Pattern Based Illumination Invariant Measure for Severe Illumination Variations.

This paper proposes a diagonal symmetric pattern (DSP) to develop the illumination invariant measure for severe illumination variations. Firstly, the subtraction of two diagonal symmetric pixels is defined as the DSP unit in the face local region, which may be positive or negative. The DSP model is obtained by combining the positive and negative DSP units. Then, the DSP model can be used to generate several DSP images based on the 4 × 4 block region by controlling the proportions of positive and negative DSP units, which results in the DSP image. The single DSP image with the arctangent function can develop the DSP-face. Multi DSP images employ the extended sparse representation classification (ESRC) as the classifier that can form the DSP images based classification (DSPC). Further, the DSP model is integrated with the pre-trained deep learning (PDL) model to construct the DSP-PDL model. Finally, the experimental results on the Extended Yale B, CMU PIE and VGGFace2 test face databases indicate that the proposed methods are efficient to tackle severe illumination variations.