Occlusion models for natural images: a statistical study of a scale invariant dead leaves model
Cached
Download Links
| Venue: | International Journal of Computer Vision |
| Citations: | 55 - 1 self |
BibTeX
@ARTICLE{Lee_occlusionmodels,
author = {Ann B. Lee and David Mumford and Jinggang Huang},
title = {Occlusion models for natural images: a statistical study of a scale invariant dead leaves model},
journal = {International Journal of Computer Vision},
year = {},
pages = {35--59}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Abstract. We develop a scale-invariant version of Matheron’s “dead leaves model ” for the statistics of natural images. The model takes occlusions into account and resembles the image formation process by randomly adding independent elementary shapes, such as disks, in layers. We compare the empirical statistics of two large databases of natural images with the statistics of the occlusion model, and find an excellent qualitative, and good quantitative agreement. At this point, this is the only image model which comes close to duplicating the simplest, elementary statistics of natural images—such as, the scale invariance property of marginal distributions of filter responses, the full co-occurrence statistics of two pixels, and the joint statistics of pairs of Haar wavelet responses. natural images, stochastic image model, non-Gaussian statistics, scaling, dead leaves model, occlu-Keywords: sions, clutter 1.
