Learning Image Alignment without Local Minima for Face Detection and Tracking - Robotics Institute Carnegie Mellon University

Learning Image Alignment without Local Minima for Face Detection and Tracking

Conference Paper, Proceedings of 8th IEEE International Conference on Automatic Face and Gesture Recognition (FG '08), September, 2008

Abstract

Active Appearance Models (AAMs) have been extensively used for face alignment during the last 20 years. While AAMs have numerous advantages relative to alternate approaches, they suffer from two major drawbacks: (i) AAMs are especially prone to local minima in the fitting process; (ii) few if any of the local minima of the cost function correspond to acceptable solutions. To minimize these problems, this paper proposes a method to learn the fitting cost function that explicitly optimizes that the local minima occur at and only at the places corresponding to the correct fitting parameters. The paper explores two methods to parameterize the cost function: pixel weighting and subspace learning. Experiments on synthetic and real data show the effectiveness of our approach for face alignment.

BibTeX

@conference{Nguyen-2008-10083,
author = {Minh Hoai Nguyen and Fernando De la Torre Frade},
title = {Learning Image Alignment without Local Minima for Face Detection and Tracking},
booktitle = {Proceedings of 8th IEEE International Conference on Automatic Face and Gesture Recognition (FG '08)},
year = {2008},
month = {September},
}