Skip to main content

Research Repository

Advanced Search

Robust and efficient parametric face alignment

Tzimiropoulos, Georgios; Zafeiriou, Stefanos; Pantic, Maja


Georgios Tzimiropoulos

Stefanos Zafeiriou

Maja Pantic


We propose a correlation-based approach to parametric object alignment particularly suitable for face analysis applications which require efficiency and robustness against occlusions and illumination changes. Our algorithm registers two images by iteratively maximizing their correlation coefficient using gradient ascent. We compute this correlation coefficient from complex gradients which capture the orientation of image structures rather than pixel intensities. The maximization of this gradient correlation coefficient results in an algorithm which is as computationally efficient as ?2 norm-based algorithms, can be extended within the inverse compositional framework (without the need for Hessian recomputation) and is robust to outliers. To the best of our knowledge, no other algorithm has been proposed so far having all three features. We show the robustness of our algorithm for the problem of face alignment in the presence of occlusions and non-uniform illumination changes. The code that reproduces the results of our paper can be found at


Tzimiropoulos, G., Zafeiriou, S., & Pantic, M. (2011). Robust and efficient parametric face alignment.

Conference Name 2011 IEEE International Conference on Computer Vision (ICCV)
End Date Nov 13, 2011
Publication Date Jan 1, 2011
Deposit Date Feb 2, 2016
Publicly Available Date Feb 2, 2016
Peer Reviewed Peer Reviewed
Public URL
Publisher URL
Additional Information © 2011 IEEE. Published in: 2011 IEEE International Conference on Computer Vision Workshops. Piscataway, N.J. : IEEE, 2011. ISBN: 9781467300629. doi: 10.1109/ICCV.2011.6126452
Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works


Downloadable Citations