Facial Expression Recognition Using Adaptive Robust Local Complete Pattern

An effective face descriptor is a significant element of a perfect facial expression recognition system. In this paper, we propose a new face descriptor, Adaptive Robust Local Complete Pattern (ARLCP). ARLCP effectively encodes significant information of emotion-related features by using the sign, magnitude and directional information of edge response that is more robust to noise and illumination variation. In this histogram-based approach, obtained feature image is divided into several regions, histogram of each region is computed independently and all histograms are concatenated to generate a final feature vector. We have experimented our method on several datasets using cross-validation schemes to evaluate the performance. From those experiments, it is evident that our method (ARLCP) provides better accuracy in facial expression recognition.