Skip to main content

Research Repository

Advanced Search

Project-out cascaded regression with an application to face alignment

Tzimiropoulos, Georgios

Project-out cascaded regression with an application to face alignment Thumbnail


Authors

Georgios Tzimiropoulos



Abstract

Cascaded regression approaches have been recently shown to achieve state-of-the-art performance for many computer vision tasks. Beyond its connection to boosting, cascaded regression has been interpreted as a learning-based approach to iterative optimization methods like the Newton’s method. However, in prior work, the connection to optimization theory is limited only in learning a mapping from image features to problem parameters. In this paper, we consider the problem of facial deformable model fitting using cascaded regression and make the following contributions: (a) We propose regression to learn a sequence of averaged Jacobian and Hessian matrices from data, and from them descent directions in a fashion inspired by Gauss-Newton optimization. (b) We show that the optimization problem in hand has structure and devise a learning strategy for a cascaded regression approach that takes the problem structure into account. By doing so, the proposed method learns and employs a sequence of averaged Jacobians and descent directions in a subspace orthogonal to the facial appearance variation; hence, we call it Project-Out Cascaded Regression (PO-CR). (c) Based on the principles of PO-CR, we built a face alignment system that produces remarkably accurate results on the challenging iBUG data set outperforming previously proposed systems by a large margin. Code for our system is available from http://www.cs.nott.ac.uk/yzt/ .

Citation

Tzimiropoulos, G. (2015). Project-out cascaded regression with an application to face alignment.

Conference Name 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
End Date Jun 12, 2015
Publication Date Jan 1, 2015
Deposit Date Jan 29, 2016
Publicly Available Date Jan 29, 2016
Peer Reviewed Peer Reviewed
Public URL https://nottingham-repository.worktribe.com/output/993197
Publisher URL http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7298989&filter=AND%28p_Publication_Number:7293313%29
Additional Information © 2015 IEEE. Published in: Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on. [Piscataway, N.J.] :IEEE, c2015. ISBN 9781467369640.

Files





Downloadable Citations