Facial complex expression recognition based on Latent Dirichlet Allocation

The Latent Dirichlet Allocation (LDA) is a model proposed recently which extracts latent topics from text data. The paper uses the LDA model in facial expression recognition but not document recognition to excavate the distribution relations between the Action Unit (AU) and expressions. Using the LDA to set up a model between AU and the facial expression of distribution relations, we can use the LDA model to ensure the unknown category of expression sequence of proportion which belongs to six basic expressions. This is the first LDA-based solution to facial complex expression recognition. We have validated that the complex facial expression recognition based on the LDA model can be used and is reasonable.