BMVC 2004, Kingston, 7th-9th Sept, 2004
Appearance factorization for facial expression analysis
B. Abboud and F. Davoine (University of Technology of Compiegne)
This paper addresses the issue of face representations for facial expression
analysis and synthesis. In this context, a global appearance model is
used and two bilinear factorization models are subsequently proposed to separate
expression and identity factors from the global appearance parameters.
A feature extraction technique inspired from the above representations is then
proposed which consists in automatically computing the optimal identity and
expression components that best adapt to an unknown target face. The proposed
representation can be seen as an alternative to the costly AAMgradient
matrix construction and iterative search and is exploited in the context of facial
expression control. Results are compared with the ones obtained using
bilinear factorization and linear regression in the space of AAM parameters.