Conference Proceeding Article
We propose a novel approach to unsupervised facial image alignment. Differently from previous approaches, that are confined to affine transformations on either the entire face or separate patches, we extract a nonrigid mapping between facial images. Based on a regularized face model, we frame unsupervised face alignment into the Lucas-Kanade image registration approach. We propose a robust optimization scheme to handle appearance variations. The method is fully automatic and can cope with pose variations and expressions, all in an unsupervised manner. Experiments on a large set of images showed that the approach is effective.
Lucas-Kanade image registration, affine transformations, robust nonrigid mapping, robust optimization scheme, unsupervised facial image alignment
Computer Sciences | Databases and Information Systems
Data Management and Analytics
IEEE 12th International Conference on Computer Vision ICCV 2009: Kyoto, Japan, 29 September - 2 October 2009
City or Country
ZHU, Jianke; VAN GOOL, Luc; and HOI, Steven C. H..
Unsupervised Face Alignment by Robust Nonrigid Mapping. (2009). IEEE 12th International Conference on Computer Vision ICCV 2009: Kyoto, Japan, 29 September - 2 October 2009. 1265-1272. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/2371
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.