Ensemble and Modular Approaches for Face Detection: A Comparison

Abstract

A new learning model based on autoassociative neural networks is developped and applied to face detection. To extend the de(cid:173) tection ability in orientation and to decrease the number of false alarms, different combinations of networks are tested: ensemble, conditional ensemble and conditional mixture of networks. The use of a conditional mixture of networks allows to obtain state of the art results on different benchmark face databases.

Cite

Text

Feraud and Bernier. "Ensemble and Modular Approaches for Face Detection: A Comparison." Neural Information Processing Systems, 1997.

Markdown

[Feraud and Bernier. "Ensemble and Modular Approaches for Face Detection: A Comparison." Neural Information Processing Systems, 1997.](https://mlanthology.org/neurips/1997/feraud1997neurips-ensemble/)

BibTeX

@inproceedings{feraud1997neurips-ensemble,
  title     = {{Ensemble and Modular Approaches for Face Detection: A Comparison}},
  author    = {Feraud, Raphaël and Bernier, Olivier},
  booktitle = {Neural Information Processing Systems},
  year      = {1997},
  pages     = {472-478},
  url       = {https://mlanthology.org/neurips/1997/feraud1997neurips-ensemble/}
}