Probabilistic Visual Learning for Object Detection

ICCV 1995 pp. 786-793

doi:10.1109/ICCV.1995.466858 /iccv/1995/moghaddam1995iccv-probabilistic/

Abstract

We present an unsupervised technique for visual learning which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. Two types of density estimates are derived for modeling the training data: a multivariate Gaussian (for a unimodal distributions) and a multivariate Mixture-of-Gaussians model (for multimodal distributions). These probability densities are then used to formulate a maximum-likelihood estimation framework for visual search and target detection for automatic object recognition. This learning technique is tested in experiments with modeling and subsequent detection of human faces and non-rigid objects such as hands.<<ETX>>

PDF ICCV Semantic Scholar

Cite

Text

Moghaddam and Pentland. "Probabilistic Visual Learning for Object Detection." IEEE/CVF International Conference on Computer Vision, 1995. doi:10.1109/ICCV.1995.466858

Markdown

[Moghaddam and Pentland. "Probabilistic Visual Learning for Object Detection." IEEE/CVF International Conference on Computer Vision, 1995.](https://mlanthology.org/iccv/1995/moghaddam1995iccv-probabilistic/) doi:10.1109/ICCV.1995.466858

BibTeX

@inproceedings{moghaddam1995iccv-probabilistic,
  title     = {{Probabilistic Visual Learning for Object Detection}},
  author    = {Moghaddam, Baback and Pentland, Alex},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1995},
  pages     = {786-793},
  doi       = {10.1109/ICCV.1995.466858},
  url       = {https://mlanthology.org/iccv/1995/moghaddam1995iccv-probabilistic/}
}