Facial Expression Recognition via Discriminative Dictionary Learning

Dictionary learning has been applied to computer vision problems such as facial expression recognition. K-SVD is one of the state-of-the-art dictionary learning algorithms. However, K-SVD is unsupervised and focuses only on the representational power. In this paper, we adopt label-consistent K-SVD with scattering transform in facial expression recognition. In addition to reducing the reconstruction error, label-consistent K-SVD combines further the discriminative sparse-code error and classification error in the optimization. Experimental results show that our approach can improve the performance of facial expression recognition when sparse coding is used.