Title :
Arbitrary facial views generation from two orthogonal facial images
Author :
Ip, Horace H S ; Yin, Li-Jun
Author_Institution :
Image Comput. Group, City Univ. of Hong Kong, Kowloon, Hong Kong
Abstract :
A new scheme for generating arbitrary views of 3D individual face automatically from side view and front view of facial images is presented in this paper. In this scheme, a generic facial model is introduced to be fit to the front and side views of the person´s head. It consists of four stages. (1) Preprocessing include facial images acquisition and feature points identification. (2) Feature extraction. (3) Computation of distortion vector field which will be used to adjust the generic facial model. (4) Synthesis of arbitrary side and front views of the individual 3D facial model and texture-mapping. The resulting individual 3D facial model will cater for various applications such as facial surgical planning and visual communication
Keywords :
face recognition; feature extraction; image texture; arbitrary facial views generation; distortion vector field; facial images acquisition; facial surgical planning; feature extraction; feature points identification; orthogonal facial images; texture-mapping; visual communication; Application software; Computer graphics; Computer science; Face; Facial features; Feature extraction; Head; Humans; Surgery; Visual communication;
Conference_Titel :
Systems, Man and Cybernetics, 1995. Intelligent Systems for the 21st Century., IEEE International Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-2559-1
DOI :
10.1109/ICSMC.1995.537913
