ML Anthology

Localizing Parts of Faces Using a Consensus of Exemplars

Peter N. Belhumeur, David W. Jacobs, David J. Kriegman, Neeraj Kumar
CVPR 2011 pp. 545-552
doi:10.1109/CVPR.2011.5995602 /cvpr/2011/belhumeur2011cvpr-localizing/

Abstract

We present a novel approach to localizing parts in images of human faces. The approach combines the output of local detectors with a non-parametric set of global models for the part locations based on over one thousand hand-labeled exemplar images. By assuming that the global models generate the part locations as hidden variables, we derive a Bayesian objective function. This function is optimized using a consensus of models for these hidden variables. The resulting localizer handles a much wider range of expression, pose, lighting and occlusion than prior ones. We show excellent performance on a new dataset gathered from the internet and show that our localizer achieves state-of-the-art performance on the less challenging BioID dataset.

CVPR Semantic Scholar

Cite

Text

Belhumeur et al. "Localizing Parts of Faces Using a Consensus of Exemplars." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995602

Markdown

[Belhumeur et al. "Localizing Parts of Faces Using a Consensus of Exemplars." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/belhumeur2011cvpr-localizing/) doi:10.1109/CVPR.2011.5995602

BibTeX

@inproceedings{belhumeur2011cvpr-localizing,
  title     = {{Localizing Parts of Faces Using a Consensus of Exemplars}},
  author    = {Belhumeur, Peter N. and Jacobs, David W. and Kriegman, David J. and Kumar, Neeraj},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {545-552},
  doi       = {10.1109/CVPR.2011.5995602},
  url       = {https://mlanthology.org/cvpr/2011/belhumeur2011cvpr-localizing/}
}