Publication Type

Conference Proceeding Article

Publication Date

10-2009

Abstract

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.

Keywords

Lucas-Kanade image registration, affine transformations, robust nonrigid mapping, robust optimization scheme, unsupervised facial image alignment

Discipline

Computer Sciences | Databases and Information Systems

Research Areas

Data Management and Analytics

Publication

IEEE 12th International Conference on Computer Vision ICCV 2009: Kyoto, Japan, 29 September - 2 October 2009

First Page

1265

Last Page

1272

ISBN

9781424444205

Identifier

10.1109/ICCV.2009.5459325

Publisher

IEEE

City or Country

Piscataway, NJ

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Additional URL

http://dx.doi.org/10.1109/ICCV.2009.5459325

Share

COinS