The Robotics Institute

Carnegie Mellon Robotics Institute

Menu

• About RI
• People
• Research
• Education
• Careers
• News & Media
• Events

• RI History

• Contact Us

• Maps & Directions

• About this Site

• Faculty

• Adjunct Faculty

• Students

• Postdoctoral Fellows

• Project Staff

• Institute Staff

• Visitors

• Alumni

• All RI Members

• Faculty Research Interests

• Research Centers

• Consortia

• Labs & Groups

• Projects

• Publications

• Academic Programs

• Admissions

• Policies and Forms

• Courses

• Student Services

• Student Life

• Faculty Positions

• Staff Positions

• Postdoctoral Positions

• Internships

• Employers Seeking Graduating Students

• Graduate Students Seeking Employment

• Official Press Releases

• Recent News

• Videos

• Events and Activities

• Talks and Seminars

Learning Patch Correspondences for Improved Viewpoint Invariant Face Recognition

Ahmed Bilal Ashraf, Simon Lucey, and Tsuhan Chen
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June, 2008.

Download

Adobe portable document format (pdf) (949KB) 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

Variation due to viewpoint is one of the key challenges that stand in the way of a complete solution to the face recognition problem. It is easy to note that local regions of the face change differently in appearance as the viewpoint varies. Recently, patch-based approaches, such as those of Kanade and Yamada, have taken advantage of this effect resulting in improved viewpoint invariant face recognition. In this paper we propose a data-driven extension to their approach, in which we not only model how a face patch varies in appearance, but also how it deforms spatially as the viewpoint varies. We propose a novel alignment strategy which we refer to as ?tack flow?that discovers viewpoint induced spatial deformities undergone by a face at the patch level. One can then view the spatial deformation of a patch as the correspondence of that patch between two viewpoints. We present improved identification and verification results to demonstrate the utility of our technique.

Notes

Associated Center(s) / Consortia: Vision and Autonomous Systems Center Associated Lab(s) / Group(s): Human Identification at a Distance Associated Project(s): Face Recognition Across Pose

Text Reference

Ahmed Bilal Ashraf, Simon Lucey, and Tsuhan Chen, "Learning Patch Correspondences for Improved Viewpoint Invariant Face Recognition," IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June, 2008.

BibTeX Reference

@inproceedings{Lucey_2008_6027,    author = "Ahmed Bilal Ashraf and Simon Lucey and Tsuhan Chen",    title = "Learning Patch Correspondences for Improved Viewpoint Invariant Face Recognition",    booktitle = "IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)",    month = "June",    year = "2008", }