Face Atlas Construction and Spatial Representation for Dynamic Expression Recognition

Dynamic facial expression recognition is subject-specific. It varies from person to person and cannot be estimated with a thresholding technique. Facial movements of different expressions are described by a diffeomorphic growth model. Salient longitudinal facial expression atlas is built for each expression by a sparse group wise image registration method, which can describe the overall facial feature changes among the whole population and can suppress the bias due to large inter-subject facial variations. The image appearance information in spatial domain and topological evolution information in temporal domain are used to guide recognition by a sparse representation method. One limitation of the proposed method is that it is still not robust enough to overcome challenges of strong illumination changes. The main reason is that the LDDMM registration algorithm do not support strong illumination changes.