Fundamental Bounds on Edge Detection: An Information Theoretic Evaluation of Different Edge Cues
Abstract
We treat the problem of edge detection as one of statistical inference. Local edge cues, implemented by filters, provide information about the likely positions of edges which can be used as input to higher-level models. Different edge cues can be evaluated by the statistical effectiveness of their corresponding filters evaluated on a dataset of 100 presegmented images. We use information theoretic measures to determine the effectiveness of a variety of different edge detectors working at multiple scales on black and white and color images. Our results give quantitative measures for the advantages of multi-level processing, for the use of chromaticity in addition to greyscale, and for the relative effectiveness of different detectors.
Cite
Text
Konishi et al. "Fundamental Bounds on Edge Detection: An Information Theoretic Evaluation of Different Edge Cues." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999. doi:10.1109/CVPR.1999.786996Markdown
[Konishi et al. "Fundamental Bounds on Edge Detection: An Information Theoretic Evaluation of Different Edge Cues." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999.](https://mlanthology.org/cvpr/1999/konishi1999cvpr-fundamental/) doi:10.1109/CVPR.1999.786996BibTeX
@inproceedings{konishi1999cvpr-fundamental,
title = {{Fundamental Bounds on Edge Detection: An Information Theoretic Evaluation of Different Edge Cues}},
author = {Konishi, Scott and Yuille, Alan L. and Coughlan, James M. and Zhu, Song Chun},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1999},
pages = {1573-1579},
doi = {10.1109/CVPR.1999.786996},
url = {https://mlanthology.org/cvpr/1999/konishi1999cvpr-fundamental/}
}