A new method for facial expression recognition based on sparse representation plus LBP

Sparse Representation-based Classification (SRC) is a newly introduced algorithm for face recognition, notable for its robust performance to occlusions and corruptions. Local Binary Patterns (LBP) is a very powerful method to describe the texture and shape of images. In this paper, we propose a novel method for facial expression recognition based on sparse representation of LBP features. Extensive experiments on Japanese Female Facial Expression (JAFFE) database are conducted. The experiment results show that the new method has a better performance than using Sparse Representation-based Classification solely on facial recognition, and is also better than those traditional algorithms such as Principal Component Analysis (PCA) and Linear discriminant analysis (LDA).