A new invariant representation of facial expressions: Definition and application to blended expression recognition

This paper proposes a novel method to perform accurate facial expression recognition by transforming the appearance space into an expression space. The expression space is computed from the person-independent organization of the facial expressions found out from data. The dimension of the expression space is reduced by the projection on a manifold compliant with the organization of the expressions. Experimental results on 14 different blended expressions show that the proposed organization based method improve the facial expression recognition performance compared to appearance based methods by 13%.