Bypassing Synthesis: PLS for Face Recognition with Pose, Low-Resolution and Sketch
Abstract
This paper presents a novel way to perform multi-modal face recognition. We use Partial Least Squares (PLS) to linearly map images in different modalities to a common linear subspace in which they are highly correlated. PLS has been previously used effectively for feature selection in face recognition. We show both theoretically and experimentally that PLS can be used effectively across modalities. We also formulate a generic intermediate subspace comparison framework for multi-modal recognition. Surprisingly, we achieve high performance using only pixel intensities as features. We experimentally demonstrate the highest published recognition rates on the pose variations in the PIE data set, and also show that PLS can be used to compare sketches to photos, and to compare images taken at different resolutions.
Cite
Text
Sharma and Jacobs. "Bypassing Synthesis: PLS for Face Recognition with Pose, Low-Resolution and Sketch." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995350Markdown
[Sharma and Jacobs. "Bypassing Synthesis: PLS for Face Recognition with Pose, Low-Resolution and Sketch." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/sharma2011cvpr-bypassing/) doi:10.1109/CVPR.2011.5995350BibTeX
@inproceedings{sharma2011cvpr-bypassing,
title = {{Bypassing Synthesis: PLS for Face Recognition with Pose, Low-Resolution and Sketch}},
author = {Sharma, Abhishek and Jacobs, David W.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2011},
pages = {593-600},
doi = {10.1109/CVPR.2011.5995350},
url = {https://mlanthology.org/cvpr/2011/sharma2011cvpr-bypassing/}
}