DocumentCode
594941
Title
Fast-accurate 3D face model generation using a single video camera
Author
Hara, Tenshi ; Kubo, Hiroshi ; Maejima, Akinobu ; Morishima, Satoru
Author_Institution
Dept. of Adv. Sci. & Eng., Waseda Univ., Tokyo, Japan
fYear
2012
fDate
11-15 Nov. 2012
Firstpage
1269
Lastpage
1272
Abstract
In this paper, we present a new method to generate a 3D face model, based on both Data-Driven and Structure-from-Motion approach. Considering both 2D frontal face image constraint, 3D geometric constraint, and likelihood constraint, we are able to reconstruct subject´s face model accurately, robustly, and automatically. Using our method, it is possible to create a 3D face model in 5.8 [sec] by only shaking own head freely in front of a single video camera.
Keywords
face recognition; image motion analysis; image reconstruction; solid modelling; video cameras; 2D frontal face image constraint; 3D geometric constraint; data-driven approach; fast-accurate 3D face model generation; likelihood constraint; structure-from-motion approach; subject face model reconstruction; video camera; Cameras; Deformable models; Face; Image reconstruction; Image sequences; Shape; Solid modeling;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location
Tsukuba
ISSN
1051-4651
Print_ISBN
978-1-4673-2216-4
Type
conf
Filename
6460370
Link To Document