4 March 2015 Weakly supervised glasses removal
Author Affiliations +
Proceedings Volume 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014); 94431J (2015) https://doi.org/10.1117/12.2178815
Event: Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 2014, Beijing, China
Abstract
Glasses removal is an important task on face recognition, in this paper, we provide a weakly supervised method to remove eyeglasses from an input face image automatically. We choose sparse coding as face reconstruction method, and optical flow to find exact shape of glasses. We combine the two processes iteratively to remove glasses more accurately. The experimental results reveal that our method works much better than these algorithms alone, and it can remove various glasses to obtain natural looking glassless facial images.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhicheng Wang, Yisu Zhou, Lijie Wen, "Weakly supervised glasses removal", Proc. SPIE 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 94431J (4 March 2015); doi: 10.1117/12.2178815; https://doi.org/10.1117/12.2178815
PROCEEDINGS
6 PAGES


SHARE
Back to Top