Title:	3D FACE RECONSTRUCTION FROM IMAGE(S) BASED ON GENDER AND ETHNICITY GENERIC MODELS
Author(s):	Zexi Liu and Fernand Cohen
ISBN:	978-989-8533-66-1
Editors:	Yingcai Xiao and Ajith P. Abraham
Year:	2017
Edition:	Single
Keywords:	3D Reconstruction; Subdivision; Ray Tracing; Pose Estimation
Type:	Full Paper
First Page:	79
Last Page:	86
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	In this paper, we describe a novel approach for creating a 3D face model from an image or images of a human face taken at a priori unknown poses using gender and ethnicity specific 3D generic face models. This process starts with a generic face model, which is morphed as images of the person become available using pre-selected point landmarks that are tessellated to form a high resolution triangular mesh. The 3D face synthesis allows for accurate pose estimation as well as face identification in 3D. The estimation of the unknown pose is achieved through the use of a Levenberg-Marquardt optimization process. Encouraging experimental results are obtained in controlled environment with high resolution images under ideal illumination condition, as well as for images taken in uncontrolled environment under arbitrary illumination with low resolution cameras.
	Go Back