Synthesized GMM Free-parts Based Face Representation for Pose Mismatch Reduction in Face Verification

Simon Lucey and C. Sanderson
tech. report , Electrical and Computer Engineering, Carnegie Mellon University, October, 2004


Download
  • Adobe portable document format (pdf) (280KB)
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
Performance of face verification systems can be adversely affected by mismatches between training and test poses, especially when only one pose is available for training. Compared to holistic/monolithic representations, we show that a ?ree-parts?representation of the face is less affected by pose changes, due to: a) some patches of a subject? face retaining similar appearance across a number of different poses, and b) those patches being able to freely move position across different poses. Furthermore, we propose that this mismatch can be reduced further by synthesizing the statistical model of a subject? ?ree-parts?representation for a set of poses for which there are no gallery observations. The synthesis is accomplished by first learning how a model for a generic frontal face transforms to represent a generic face at a particular non-frontal pose. The learned transformation is then applied to each subject? frontal model to synthesize a non-frontal model. The original and synthesized models are then concatenated in order to automatically handle multiple poses.

Notes
Associated Center(s) / Consortia: Vision and Autonomous Systems Center
Associated Lab(s) / Group(s): Face Group
Number of pages: 8

Text Reference
Simon Lucey and C. Sanderson, "Synthesized GMM Free-parts Based Face Representation for Pose Mismatch Reduction in Face Verification," tech. report , Electrical and Computer Engineering, Carnegie Mellon University, October, 2004

BibTeX Reference
@techreport{Lucey_2004_5280,
   author = "Simon Lucey and C. Sanderson",
   title = "Synthesized GMM Free-parts Based Face Representation for Pose Mismatch Reduction in Face Verification",
   booktitle = "",
   institution = "Electrical and Computer Engineering",
   month = "October",
   year = "2004",
}