Robust Face Recognition under Different Facial Expressions, Illumination Variations and Partial Occlusions

In this paper, a robust face recognition system is presented, which can perform precise face recognition under facial expression variations, illumination changes, and partial occlusions. The embedded hidden Markov model based face classifier is applied for identity recognition in which the proposed observation extraction is presented by performing local binary patterns prior to performing delta operation on the discrete cosine transform coefficients of consecutive blocks. Experimental results show that the proposed face recognition system achieves high recognition accuracy of 99%, 96.6% and 98% under neutral face, expression variations, and illumination changes respectively. Particularly, under partial occlusions, the system achieves recognition rate of 81.6% and 86.6% for wearing sunglasses and scarf respectively.