Wide-Baseline Stereo for Face Recognition with Large Pose Variation
Abstract
2-D face recognition in the presence of large pose variations presents a significant challenge. When comparing a frontal image of a face to a near profile image, one must cope with large occlusions, non-linear correspondences, and significant changes in appearance due to viewpoint. Stereo matching has been used to handle these problems, but performance of this approach degrades with large pose changes. We show that some of this difficulty is due to the effect that foreshortening of slanted surfaces has on window-based matching methods, which are needed to provide robustness to lighting change. We address this problem by designing a new, dynamic programming stereo algorithm that accounts for surface slant. We show that on the CMU PIE dataset this method results in significant improvements in recognition performance.
Cite
Text
Castillo and Jacobs. "Wide-Baseline Stereo for Face Recognition with Large Pose Variation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995559Markdown
[Castillo and Jacobs. "Wide-Baseline Stereo for Face Recognition with Large Pose Variation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/castillo2011cvpr-wide/) doi:10.1109/CVPR.2011.5995559BibTeX
@inproceedings{castillo2011cvpr-wide,
title = {{Wide-Baseline Stereo for Face Recognition with Large Pose Variation}},
author = {Castillo, Carlos Domingo and Jacobs, David W.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2011},
pages = {537-544},
doi = {10.1109/CVPR.2011.5995559},
url = {https://mlanthology.org/cvpr/2011/castillo2011cvpr-wide/}
}