Learning to identify and track faces in image sequences

G.J. Edwards, C.J. Taylor, T.F. Cootes
Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)  
We address the problem of robust face identification in the presence of pose, lighting, and expression variation. Previous approaches to the problem have assumed similar models of variation for each individual, estimated from pooled training data. We describe a method of updating a first order global estimate of identity by learning the classspecific correlation between the estimate and the residual variation during a sequence. This is integrated with an optimal tracking scheme, in which
more » ... y variation is decoupled from pose, lighting and expression variation. The method results in robust tracking and a more stable estimate of facial identity under changing conditions.
doi:10.1109/iccv.1998.710737 dblp:conf/iccv/EdwardsTC98 fatcat:wwylgdvptjbrvo3k4opradtopq