Deriving facial articulation models from image sequences

Author

Tao, Hai ; Huang, Thomas S.

Author_Institution

Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA

fYear

1998

fDate

4-7 Oct 1998

Firstpage

158

Abstract

Human facial articulation models are derived from frontal and side view image sequences using a connected vibrations non-rigid motion tracking algorithm. First, a 3D head geometric model is fitted to the face subject in the initial frame. The face model is masked with multiple planar membrane patches that are connected with each other. Then, the in-plate facial motions in the image sequences are computed from an over-determined system. Finally, this information is exploited for creating or customizing a facial articulation model

Keywords

image motion analysis; image sequences; tracking; vibrations; video signal processing; 3D head geometric model; connected vibrations nonrigid motion tracking algorithm; face model; frontal view; human facial articulation models; image sequences; in-plate facial motions; multiple planar membrane patches; over-determined system; side view; video sequences; Biomembranes; Deformable models; Facial animation; Finite element methods; Head; Humans; Image sequences; Least squares approximation; Shape; Solid modeling; Speech; Tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on

Conference_Location

Chicago, IL

Print_ISBN

0-8186-8821-1

Type

conf

DOI

10.1109/ICIP.1998.727158

Filename

727158