Modelling Faces Dynamically across Views and Over Time

A comprehensive novel multi-view dynamic face model is presented in this paper to address two challenging problems in face recognition and facial analysis: modelling faces with large pose variation and modelling faces dynamically in video sequences. The model consists of a sparse 3D shape model learnt from 2D images, a shape-and-posefree texture model, and an affine geometrical model. Model fitting is performed by optimising (1) a global fitting criterion on the overall face appearance whilst it changes across views and over time, (2) a local fitting criterion on a set of landmarks, and (3) a temporal fitting criterion between successive frames in a video sequence. By temporally estimating the model parameters over a sequence input, the identity and geometrical information of a face is extracted separately. The former is crucial to face recognition and facial analysis. The latter is used to aid tracking and aligning faces. We demonstrate the results of successfully applying this model...

• Type: Conference
• Year: 2001
• Where: ICCV
• Authors: Yongmin Li, Shaogang Gong, Heather M. Liddell
• Keywords: Affine Geometrical Model, Computer Vision, Dynamic Face Model, Global Fitting Criterion, ICCV 2001, Model Fitting, Temporal Fitting Criterion