Illumination Invariant Multi-pose Face Tracking

A novel face tracking algorithm is proposed which is less insensitive to large face appearance variation caused by lighting and viewpoints. The proposed dynamic face appearance model includes an illumination invariant pose manifold to represent the pose nonlinearity and an object-specific incremental multi-pose face model. The pose manifold is built with the patch alignment algorithm, where the tensor based illumination reduction is used to define the local patch. Particularly, the probability of the face belonging to the pose manifold can be used for choosing the object-specific face model. The experimental results show the face tracking model can successfully track faces under unseen poses and changing illuminations.