Evaluating Error Functions for Robust Active Appearance Models

April 2006

Evaluating Error Functions for Robust Active Appearance Models

Authors:

Barry-John Theobald, Iain Matthews, and Simon Baker

Abstract:

Active appearance models (AAMs) are generative parametric models commonly used to track faces in video sequences. A limitation of AAMs is they are not robust to occlusion. A recent extension reformulated the search as an iteratively re-weighted least-squares problem. In this paper we focus on the choice of error function for use in a robust AAM search. We evaluate eight error functions using two performance metrics: accuracy of occlusion detection and fitting robustness. We show for any reasonable error function the performance in terms of occlusion detection is the same. However, this does not mean that fitting performance will be the same. We describe experiments for measuring fitting robustness for images containing real occlusion. The best approach assumes the residuals at each pixel are Gaussianaly distributed, then estimates the parameters of the distribution from images that do not contain occlusion. In each iteration of the search, the error image is used to sample these distributions to obtain the pixel weights.
@conference{Theobald-2006-9430,
author = {Barry-John Theobald And Iain Matthews And Simon Baker},
title = {Evaluating Error Functions for Robust Active Appearance Models},
booktitle = {Proceedings of 7th International Conference on Automatic Face & Gesture Recognition (FG '06)},
year = {2006},
month = {April},
pages = {149 - 154},
}
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.