Toward a Full Probability Model of Edges in Natural Images
Abstract
We investigate the statistics of local geometric structures in natural images. Previous studies [ 13 , 14 ] of high-contrast 3×3 natural image patches have shown that, in the state space of these patches, we have a concentration of data points along a low-dimensional non-linear manifold that corresponds to edge structures. In this paper we extend our analysis to a filter-based multiscale image representation, namely the local 3-jet of Gaussian scale-space representations. A new picture of natural image statistics seems to emerge, where primitives (such as edges, blobs, and bars) generate low-dimensional non-linear structures in the state space of image data.
Cite
Text
Pedersen and Lee. "Toward a Full Probability Model of Edges in Natural Images." European Conference on Computer Vision, 2002. doi:10.1007/3-540-47969-4_22Markdown
[Pedersen and Lee. "Toward a Full Probability Model of Edges in Natural Images." European Conference on Computer Vision, 2002.](https://mlanthology.org/eccv/2002/pedersen2002eccv-full/) doi:10.1007/3-540-47969-4_22BibTeX
@inproceedings{pedersen2002eccv-full,
title = {{Toward a Full Probability Model of Edges in Natural Images}},
author = {Pedersen, Kim Steenstrup and Lee, Ann B.},
booktitle = {European Conference on Computer Vision},
year = {2002},
pages = {328-342},
doi = {10.1007/3-540-47969-4_22},
url = {https://mlanthology.org/eccv/2002/pedersen2002eccv-full/}
}