Statistics of Natural Images and Models

CVPR 1999 pp. 1541-1547

doi:10.1109/CVPR.1999.786990 /cvpr/1999/huang1999cvpr-statistics/

Abstract

Large calibrated datasets of 'random' natural images have recently become available. These make possible precise and intensive statistical studies of the local nature of images. We report results ranging from the simplest single pixel intensity to joint distribution of 3 Haar wavelet responses. Some of these statistics shed light on old issues such as the near scale-invariance of image statistics and some are entirely new. We fit mathematical models to some of the statistics and explain others in terms of local image features.

PDF CVPR Semantic Scholar

Cite

Text

Huang and Mumford. "Statistics of Natural Images and Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999. doi:10.1109/CVPR.1999.786990

Markdown

[Huang and Mumford. "Statistics of Natural Images and Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999.](https://mlanthology.org/cvpr/1999/huang1999cvpr-statistics/) doi:10.1109/CVPR.1999.786990

BibTeX

@inproceedings{huang1999cvpr-statistics,
  title     = {{Statistics of Natural Images and Models}},
  author    = {Huang, Jinggang and Mumford, David},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1999},
  pages     = {1541-1547},
  doi       = {10.1109/CVPR.1999.786990},
  url       = {https://mlanthology.org/cvpr/1999/huang1999cvpr-statistics/}
}