3D FACIAL DYNAMICS EXTRACTION

A human face is a bumpy and mobile surface. Neither 2D dynamic data nor 3D static data may be sufficient to depict such a property. 3D static face models lacking a temporal context may be a profound handicap to recognizing facial expressions.

The first 3D dynamic facial expression database was created in 2008 by Yin et al. (Yin et al., 2008). All reported approaches were based on in-house 3D dynamic data sets. In our works, we use a common 3 D deformable face model Candide (Ahlberg, 2002). Despite the simplicity of this 3D wireframe model, it can be used to extract a subset of 3D facial dynamics in real time using one single camera. Once the 3D facial dynamics are learned the recognition scheme should use the same 3D face model.