3D facial animation from Chinese text

Author

Li, Nan ; Bu, Jiajun ; Chen, Chun ; Liang, Ronghua

Author_Institution

Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China

Volume

4

fYear

2003

fDate

5-8 Oct. 2003

Firstpage

3738

Abstract

The reality and controllability of the facial animation are enhanced in our work by modeling mouth in a parametric approach described by 7 parameters: superior and anterior bend for upper and lower lip, width of the mouth, weight of radium of lips. These parameters were calculated by tracking only 4 points around the mouth from video, and the cost of computation is low. The coarticulation model of Cohen and Massaro was adopted to generate the natural key frames and the transitional frames. Considering the difference between Chinese and English, an algorithm was introduced to calculate the coefficients of dominance functions. Based on the muscle-based facial model and the parametric mouth model, the 3D head can talk vividly.

Keywords

computer animation; face recognition; image reconstruction; speech recognition; 3D facial animation; 3D reconstruction; Chinese text; coarticulation model; dominance functions coefficients; face tracking; mouth modeling; muscle-based facial model; natural key frames; parameterization; transitional frames; viseme selection; Computational efficiency; Computer interfaces; Computer science; Educational institutions; Facial animation; Interpolation; Mouth; Muscles; Speech analysis; Springs;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2003. IEEE International Conference on

ISSN

1062-922X

Print_ISBN

0-7803-7952-7

Type

conf

DOI

10.1109/ICSMC.2003.1244470

Filename

1244470