Face Alignment through Subspace Constrained Mean-Shifts

September 2009

Face Alignment through Subspace Constrained Mean-Shifts

Authors:

Jason M. Saragih, Simon Lucey, and Jeffrey Cohn
Conference Paper
Proceedings of (ICCV) International Conference on Computer Vision

Abstract:

Deformable model fitting has been actively pursued in the computer vision community for over a decade. As a result, numerous approaches have been proposed with varying degrees of success. A class of approaches that has shown substantial promise is one that makes independent predictions regarding locations of the model’s landmarks, which are combined by enforcing a prior over their joint motion. A common theme in innovations to this approach is the replacement of the distribution of probable landmark locations, obtained from each local detector, with simpler parametric forms. This simplification substitutes the true objective with a smoothed version of itself, reducing sensitivity to local minima and outlying detections. In this work, a principled optimization strategy is proposed where a non-parametric representation of the landmark distributions is maximized within a hierarchy of smoothed estimates. The resulting update equations are reminiscent of mean-shift but with a subspace constraint placed on the shape’s variability. This approach is shown to outperform other existing methods on the task of generic face fitting.
@conference{Saragih-2009-10311,
author = {Jason M. Saragih And Simon Lucey And Jeffrey Cohn},
title = {Face Alignment through Subspace Constrained Mean-Shifts},
booktitle = {Proceedings of (ICCV) International Conference on Computer Vision},
year = {2009},
month = {September},
pages = {1034 - 1041},
keywords = {Constrained Local Models, Face Alignment},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.