ML Anthology

An Image-Based Bayesian Framework for Face Detection

Lingmin Meng, Truong Q. Nguyen, David A. Castañón
CVPR 2000 pp. 1302-1307
doi:10.1109/CVPR.2000.855833 /cvpr/2000/meng2000cvpr-image/

Abstract

In this paper, we present a novel approach for frontal face detection in gray-scale images. We represent both faces and clutter by using two-dimensional wavelet decomposition. To characterize the statistical dependency between different levels of wavelet, we introduce a Hidden Markov Model (HMM), in which a number of discrete states at each level capture the diversity of faces as well as clutter. Our experiments indicate that the proposed algorithm outperforms conventional template-based methods such as matched filter and eigenface methods.

CVPR Semantic Scholar

Cite

Text

Meng et al. "An Image-Based Bayesian Framework for Face Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.855833

Markdown

[Meng et al. "An Image-Based Bayesian Framework for Face Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/meng2000cvpr-image/) doi:10.1109/CVPR.2000.855833

BibTeX

@inproceedings{meng2000cvpr-image,
  title     = {{An Image-Based Bayesian Framework for Face Detection}},
  author    = {Meng, Lingmin and Nguyen, Truong Q. and Castañón, David A.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2000},
  pages     = {1302-1307},
  doi       = {10.1109/CVPR.2000.855833},
  url       = {https://mlanthology.org/cvpr/2000/meng2000cvpr-image/}
}