Dr. Fatos Berisha

Fatos focused his research on component analysis of facial motion. Facial occlusions can cause both human observers and computer algorithms to fail in a variety of important tasks such as facial action analysis and expression classification. This is because the missing information is not reconstructed accurately enough for the purpose of the task in hand. Most current computer methods that are used to tackle this problem implement complex three-dimensional polygonal face models that are generally timeconsuming to produce and unsuitable for photorealistic reconstruction of missing facial features and behaviour. In his thesis, Fatos adopted an image-based approach to solve the occlusion problem. A dynamic computer model of the face was used to retrieve the occluded facial information from the driver faces. The model consisted of a set of orthogonal basis actions obtained by application of principal component analysis (PCA) on image changes and motion fields extracted from a sequence of natural facial motion. Examples of occlusion affected facial behaviour could then be projected onto the model to compute coefficients of the basis actions and thus produce photorealistic performance-driven animations.

Fatos found that the most important areas were those around and including the mouth and eyes. These regions overlapped but were not identical to areas of maximum pixel-value variance. His research showed that the PCA face model recovers aspects of expressions in those areas occluded in the driver sequence, but the expression is generally muted. 

Page last modified on 06 sep 09 22:43