Facial expression recognition and synthesis based on an appearance model

Bouchra Abboud (1) , Franck Davoine (1) , Mô Dang (1)

1 Heudiasyc - Heuristique et Diagnostic des Systèmes Complexes [Compiègne]

This article addresses the issue of expressive face modelling using an active appearance model for facial expression recognition and synthesis. We consider the six universal emotional categories namely joy, anger, fear, disgust, sadness and surprise. After a description of the active appearance model (computed with 3 or only one PCA), we address the active appearance model contribution to automatic facial expression recognition. Then we propose a new method for analysis and synthesis allowing, from a single photo, to cancel the facial expression on a given face and to artificially synthesize novel expressions on this same face. In this last framework, we propose two facial expression modelling approaches.

Mots clés: Face representation; Appearance models; Facial expression recognition; Facial expression synthesis

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Bouchra Abboud, Franck Davoine, Mô Dang. Facial expression recognition and synthesis based on an appearance model. Signal Processing: Image Communication, 2004, 19 (8), pp.723-740. ⟨10.1016/j.image.2004.05.009⟩. ⟨hal-00143335⟩