Is Face Recognition Really a Compressive Sensing Problem?

Qinfeng Shi, Anders P. Eriksson, Anton van den Hengel, Chunhua Shen

CVPR 2011 pp. 553-560

doi:10.1109/CVPR.2011.5995556 /cvpr/2011/shi2011cvpr-face/

Abstract

Compressive Sensing has become one of the standard methods of face recognition within the literature. We show, however, that the sparsity assumption which underpins much of this work is not supported by the data. This lack of sparsity in the data means that compressive sensing approach cannot be guaranteed to recover the exact signal, and therefore that sparse approximations may not deliver the robustness or performance desired. In this vein we show that a simple £2 approach to the face recognition problem is not only significantly more accurate than the state-of-the-art approach, it is also more robust, and much faster. These results are demonstrated on the publicly available YaleB and AR face datasets but have implications for the application of Compressive Sensing more broadly.

PDF CVPR Semantic Scholar

Cite

Text

Shi et al. "Is Face Recognition Really a Compressive Sensing Problem?." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995556

Markdown

[Shi et al. "Is Face Recognition Really a Compressive Sensing Problem?." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/shi2011cvpr-face/) doi:10.1109/CVPR.2011.5995556

BibTeX

@inproceedings{shi2011cvpr-face,
  title     = {{Is Face Recognition Really a Compressive Sensing Problem?}},
  author    = {Shi, Qinfeng and Eriksson, Anders P. and van den Hengel, Anton and Shen, Chunhua},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {553-560},
  doi       = {10.1109/CVPR.2011.5995556},
  url       = {https://mlanthology.org/cvpr/2011/shi2011cvpr-face/}
}