ML Anthology

Neural Network-Based Face Detection

Henry A. Rowley, Shumeet Baluja, Takeo Kanade
CVPR 1996 pp. 203-208
doi:10.1109/CVPR.1996.517075 /cvpr/1996/rowley1996cvpr-neural/

Abstract

We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We use a bootstrap algorithm for training the networks, which adds false detections into the training set as training progresses. This eliminates the difficult task of manually selecting non-face training examples, which must be chosen to span the entire space of non-face images. Comparisons with other state-of-the-art face detection systems are presented; our system has better performance in terms of detection and false-positive rates.

CVPR Semantic Scholar

Cite

Text

Rowley et al. "Neural Network-Based Face Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996. doi:10.1109/CVPR.1996.517075

Markdown

[Rowley et al. "Neural Network-Based Face Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996.](https://mlanthology.org/cvpr/1996/rowley1996cvpr-neural/) doi:10.1109/CVPR.1996.517075

BibTeX

@inproceedings{rowley1996cvpr-neural,
  title     = {{Neural Network-Based Face Detection}},
  author    = {Rowley, Henry A. and Baluja, Shumeet and Kanade, Takeo},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1996},
  pages     = {203-208},
  doi       = {10.1109/CVPR.1996.517075},
  url       = {https://mlanthology.org/cvpr/1996/rowley1996cvpr-neural/}
}