Abstract

A training process for facial expression recognition is usually performed sequentially in three individual stages: feature learning, feature selection, and classififier construction. Extensive empirical studies are needed to search for an optimal combination of feature representation, feature set, and classififier to achieve good recognition performance. This paper presents a novel Boosted Deep Belief Network (BDBN) for performing the three training stages iteratively in a unifified loopy framework. Through the proposed BDBN framework, a set of features, which is effective to characterize expression-related facial appearance/shape changes, can be learned and selected to form a boosted strong classififier in a statistical way. As learning continues, the strong classififier is improved iteratively and more importantly, the discriminative capabilities of selected features are strengthened as well according to their relative importance to the strong classififier via a joint fifine-tune process in the BDBN framework. Extensive experiments on two public databases showed that the BDBN framework yielded dramatic improvements in facial expression analysis.