Title :
3D face reconstruction from one side-view face images
Author :
Jaeik Jo ; Yu Jin Jung ; Jaihie Kim
Author_Institution :
Biometrics Eng. Res. Center, Yonsei Univ., Seoul, South Korea
Abstract :
This paper presents a 3D face reconstruction method from one side-view face images. In order to reconstruct 3D face, Structure from Motion (SfM) method, which has widely used to reconstruct 3D face, and bilateral symmetry of human face are used. In the experiments, the reconstructed 3D facial shape is quantitatively compared with the 3D facial shape obtained from a 3D scanner, and the results show that the proposed method is very useful to reconstruct an accurate 3D face when only one side-view face images are available.
Keywords :
face recognition; image reconstruction; 3D face reconstruction method; 3D facial shape; 3D scanner; bilateral symmetry; one side-view face images; structure from motion method; Face; Face recognition; Feature extraction; Image reconstruction; Reconstruction algorithms; Shape; Three-dimensional displays; 3D face reconstruction; active appearance model; bilateral symmetry; structure form motion;
Conference_Titel :
Electronics, Information and Communications (ICEIC), 2014 International Conference on
Conference_Location :
Kota Kinabalu
DOI :
10.1109/ELINFOCOM.2014.6914359