The Asymmetry of Image Registration and its Application to Face Tracking

Goksel Dedeoglu, Takeo Kanade, and Simon Baker
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29, No. 5, May, 2007, pp. 807-823.


Download
  • Adobe portable document format (pdf) (4MB)
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.

Abstract
Most image registration problems are formulated in an asymmetric fashion. Given a pair of images, one is implicitly or explicitly regarded as a template, and warped onto the other to match as well as possible. In this paper, we focus on this seemingly arbitrary choice of the roles, and reveal how it may lead to biased warp estimates in the presence of relative scaling. We present a principled way of selecting the template, and explain why only the correct asymmetric form, with the potential inclusion of a blurring step, can yield an unbiased estimator.

We validate our analysis in the domain of model-based face tracking. We show how the usual Active Appearance Model (AAM) formulation overlooks the asymmetry issue, causing the fitting accuracy to degrade quickly when the observed objects are smaller than their model. We formulate a novel, ``resolution-aware fitting'' (RAF) algorithm that respects the asymmetry, and incorporates an explicit model of the blur caused by the camera's sensing elements into the fitting formulation. We compare the RAF algorithm against a state-of-the-art tracker across a variety of resolutions and AAM complexity levels. Experimental results show that RAF significantly improves the estimation accuracy of both shape and appearance parameters when fitting to low resolution data.

Recognizing and accounting for the asymmetry of image registration leads to tangible accuracy improvements in analyzing low resolution imagery.


Keywords
Image registration, resolution, estimation bias, Active Appearance Models

Notes
Associated Center(s) / Consortia: Vision and Autonomous Systems Center
Associated Lab(s) / Group(s): Face Group
Associated Project(s): Image Enhancement for Faces
Number of pages: 17

Text Reference
Goksel Dedeoglu, Takeo Kanade, and Simon Baker, "The Asymmetry of Image Registration and its Application to Face Tracking," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29, No. 5, May, 2007, pp. 807-823.

BibTeX Reference
@article{Dedeoglu_2007_5720,
   author = "Goksel Dedeoglu and Takeo Kanade and Simon Baker",
   title = "The Asymmetry of Image Registration and its Application to Face Tracking",
   journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
   pages = "807-823",
   publisher = "IEEE Computer Society",
   address = "Los Alamitos, CA",
   month = "May",
   year = "2007",
   volume = "29",
   number = "5",
}