Abstract. This paper presents a prototype system, which synthesizes entertainment-oriented cartoon face and translates text message to multimedia animation in mobile phone. While a digital real facial photograph and some text are imputed, a piece of exaggerated facial animation with entertainment will be shown in the phone. Three steps are used to get this entertainment effect: first is the illustration generation of the real face image, General-Scale-Edge (GSE) is adopted to take various scale of the edge into account, which can extract the feature edge on human’s face efficiently. The second is the expression warping to produce a caricature. The improved feature based warping method is employed. Finally, we generate the exaggerated facial animation based on the caricature using TTVS method. In addition, we improved modified Active Shape Model to remove the background and control more feature points on the face. Experiments show the system work well with high performance on the PDA....