PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Appearance factorization based facial expression recognition and synthesis
Bouchra Abboud and Franck Davoine
In: 17th International Conference on Pattern Recognition, 23-26 August 2004, Cambridge, U.K..


Facial expression interpretation, recognition and analysis is a key issue in visual communication and man to machine interaction. In this paper, we address the issues of facial expression recognition and synthesis and compare the proposed bilinear factorization based representations with previously investigated methods such as linear discriminant analysis and linear regression. We conclude that bilinear factorization outperforms these techniques in terms of correct recognition rates and synthesis photorealism especially when the number of training samples is restrained.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:User Modelling for Computer Human Interaction
Learning/Statistics & Optimisation
ID Code:507
Deposited By:Franck Davoine
Deposited On:01 January 2005