Robust hybrid framework for automatic facial expression recognition

摘要

Over the last few years, facial expression recognition is an active research field, which has an extensive?range of applications in the?area?of?social interaction, social intelligence, autism?detection and?Human-computer interaction. In this paper, a robust hybrid framework is presented to recognize the facial expressions, which enhances the efficiency and speed of recognition system by extracting significant features of a face. In the proposed framework, feature representation and extraction are done by using Local Binary Patterns (LBP) and Histogram of Oriented Gradients (HOG). Later, the dimensionalities of the obtained features are reduced using Compressive Sensing (CS) algorithm and classified using multiclass SVM classifier. We investigated the performance of the proposed hybrid framework on two public databases such as CK+ and JAFFE data sets. The investigational results show that the proposed hybrid framework is a promising framework for?recognizing?and identifying facial expressions with varying illuminations and poses in real time.