Title :
A Fully Automatic Approach to Facial Feature Tracking Based on Image Registration
Author :
Feng, Xuetao ; Wang, Yangsheng ; Ding, Bin ; Wang, Xiaoyan
Author_Institution :
Inst. of Autom., Chinese Acad. of Sci., Beijing
Abstract :
This paper presents a real time, fully automatic facial feature detection and tracking approach. The head pose and facial action is tracked by a modified Candide 3D wireframe model based on an improved image registration technique. An effective model shape and position initialization method is also proposed. Experimental results demonstrate that our system is accurate, robust and fast enough for common applications, even when there are great pose and expression variations.
Keywords :
emotion recognition; face recognition; feature extraction; image registration; pose estimation; tracking; Candide 3D wireframe model; automatic facial feature detection; automatic facial feature tracking; facial expression tracking; head pose tracking; image registration; model shape; position initialization method; Active appearance model; Cameras; Computer vision; Deformable models; Face detection; Facial features; Head; Image registration; Robustness; Shape;
Conference_Titel :
Image Analysis for Multimedia Interactive Services, 2008. WIAMIS '08. Ninth International Workshop on
Conference_Location :
Klagenfurt
Print_ISBN :
978-0-7695-3344-5
Electronic_ISBN :
978-0-7695-3130-4
DOI :
10.1109/WIAMIS.2008.6
