Sciweavers

ICIP
2000
IEEE

Individual 3D Face Synthesis Based on Orthogonal Photos and Speech-Driven Facial Animation

13 years 7 months ago
Individual 3D Face Synthesis Based on Orthogonal Photos and Speech-Driven Facial Animation
In the paper, a methodology for individual face synthesis using given orthogonal photos is proposed. And an integrated speech-driven facial animation system is presented. Firstly, in order to capture given subject’s personal facial configuration, a novel coarse-to-fine strategy based on facial texture and deformable template is proposed to localize some facial feature points in the image of frontal view. And the corresponding feature points in the profile are extracted by using polygonal approximation. Secondly, all these feature points are aligned to fit the generic 3D face model to a specialized one to reflect the given person's facial configuration. Then a multi-direction texture-mapping technique is presented to synthesize a lifelike personal face. Finally, muscle-based expression and lip-motion models are built up. All above technologies are integrated into a speech-driven face animation system. We are aiming at a MPEG-4 compatible video-driven face animation system.
Shiguang Shan, Wen Gao, Jie Yan, Hongming Zhang, X
Added 31 Jul 2010
Updated 31 Jul 2010
Type Conference
Year 2000
Where ICIP
Authors Shiguang Shan, Wen Gao, Jie Yan, Hongming Zhang, Xilin Chen
Comments (0)