Individual facial expression transferring using Active Appearance Model and FAP in MPEG-4

This paper presents a facial expression transferring system. The inputs of the system are an expression picture and a neutral picture of a single frontal face, which are captured by an ordinary video camera. And the output is a 3D individual face with the same expression. We design and implement the system using FDPs and FAPs in MPEG-4 and the Active Appearance Models (AAMs) comprehensively. Firstly, Adaboost method is used to detect the face. Then 68 feature points of the face are located with the algorithm based on active appearance models (AAM). With these feature points and according to the MPEG-4 standard, 2D facial expression feature data are registered to FAPs in MPEG-4 by image normalization and feature alignment. After that, the FAPs can be used to drive the MPEG-4 compatible models and conduct 3D face with the corresponding expression.