Fragmentation in the Vision of Scenes
Abstract
Natural images are highly structured in their spatial configuration. Where one would expect a different spatial distribution for every image, as each image has a different spatial layout, we show that the spatial statistics of recorded images can be explained by a single process of sequential fragmentation. The observation by a resolution limited sensory system turns out to have a profound influence on the observed statistics of natural images. The power-law and normal distribution represent the extreme cases of sequential fragmentation. Between these two extremes, spatial detail statistics deform from power-law to normal through the Weibull type distribution as receptive field size increases relative to image detail size.
Cite
Text
Geusebroek and Smeulders. "Fragmentation in the Vision of Scenes." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238326Markdown
[Geusebroek and Smeulders. "Fragmentation in the Vision of Scenes." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/geusebroek2003iccv-fragmentation/) doi:10.1109/ICCV.2003.1238326BibTeX
@inproceedings{geusebroek2003iccv-fragmentation,
title = {{Fragmentation in the Vision of Scenes}},
author = {Geusebroek, Jan-Mark and Smeulders, Arnold W. M.},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2003},
pages = {130-135},
doi = {10.1109/ICCV.2003.1238326},
url = {https://mlanthology.org/iccv/2003/geusebroek2003iccv-fragmentation/}
}