Unsupervised Face Alignment by Robust Nonrigid Mapping

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.

• Type: Conference
• Year: 2009
• Where: ICCV
• Authors: Jianke Zhu, Luc Van Gool and Steven C. H. Hoi
• Keywords: Computer Vision, ICCV 2009, Nonrigid Mapping, Unsupervised Face Alignment