Carnegie Mellon Robotics Institute
Ralph Gross, Iain Matthews, and Simon Baker
Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition, May, 2002, pp. 1 - 7.
| Download |
|
| Abstract |
| In many face recognition tasks the pose of the probe and gallery images are different. In other cases multiple gallery or probe images may be available, each captured from a different pose. We propose a face recognition algorithm which can use any number of gallery images per subject captured at arbitrary poses, and any number of probe images, again captured at arbitrary poses. The algorithm operates by estimating the eigen light-field of the subject's head from the input gallery or probe images. Matching between the probe and gallery is then performed using the eigen light-fields. We present results on the CMU PIE and the FERET face databases. |
| Keywords |
| Face recognition across pose, eigen light-fields, appearance-based object recognition, image re-rendering. |
| Notes |
Sponsor: Office of Naval Research Grant ID: N00014-00-1-0915 Associated Center(s) / Consortia:
Vision and Autonomous Systems Center Associated Lab(s) / Group(s):
Human Identification at a Distance, Face Group, Component Analysis Associated Project(s):
Light-fields, Face Recognition Across Pose, Face Recognition Number of pages: 8 |
| Text Reference |
| Ralph Gross, Iain Matthews, and Simon Baker, "Eigen Light-Fields and Face Recognition Across Pose," Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition, May, 2002, pp. 1 - 7. |
| BibTeX Reference |
|
@inproceedings{Gross_2002_3920, author = "Ralph Gross and Iain Matthews and Simon Baker", title = "Eigen Light-Fields and Face Recognition Across Pose", booktitle = "Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition", pages = "1 - 7", month = "May", year = "2002", } |
| The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University. Contact Us | Update Instructions |