Learning a Class-Specific Dictionary for Facial Expression Recognition

Sparse coding is currently an active topic in signal processing and pattern recognition. MetaFace Learning (MFL) is a typical sparse coding method and exhibits promising performance for classification. Unfortunately, due to using the l(1)-norm minimization, MFL is expensive to compute and is not robust enough. To address these issues, this paper proposes a faster and more robust version of MFL with the l(2)-norm regularization constraint on coding coefficients. The proposed method is used to learn a class-specific dictionary for facial expression recognition. Extensive experiments on two popular facial expression databases, i.e., the JAFFE database and the Cohn-Kanade database, demonstrate that our method shows promising computational efficiency and robustness on facial expression recognition tasks.