3D Reconstruction of Face Using Front View and Side View Images

Please enable javascript in your browser.

Nowrozi, Danial | 2012

843 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 43027 (02)
University: Sharif University of Technology
Department: Mathematical Science
Advisor(s): Ramezanin, Rassul; Jamzad, Mansour
Abstract:
3D face modeling is currently a popular area in Computer Graphics and Computer Vision. Many techniques have been introduced for this purpose, such as using one or more cameras, 3D scanners, and many other systems of sophisticated hardware with related software. But the main goal is to find a good balance between visual reality and the cost of the system. In this thesis, reconstruction of a 3D human face from a pair of orthogonal views, front face and side face is studied. Unlike many other systems, facial feature points are obtained automatically from two photographs with the help of an Active shape model algorithm for the frontal face and an edge detection algorithm for side view of the face. It is seen that using ASM provides also enough feature points to derive a 3D face roughly, and then these points are used to fit a generic face mesh for a more realistic model. To cover this 3D model, a single texture image is generated from the initial photographs
Keywords:
Active Shape Model ; Three Dimensional Reconstruction ; Human Face ; Skin Segmentation ; Face Localization ; Texture Mapping ; Deformable Mesh Model

No TOC