ML Anthology

Adaptive Estimation of Hysteresis Thresholds

Edwin R. Hancock, Josef Kittler
CVPR 1991 pp. 196-201
doi:10.1109/CVPR.1991.139687 /cvpr/1991/hancock1991cvpr-adaptive/

Abstract

It is shown that the hitherto heuristic hysteresis linking idea of J.F. Canny (1986) can be formulated as a Bayesian contextual decision process. This approach draws on an explicit image model which accounts both for the way in which noisy raw-edge information is characterized via filtering operations and how the required edge-connectivity information is quantified. The main advantage is that the previously ad hoc hysteresis thresholds can be related to the parameters of an image model. One feature is the requirement of a third hysteresis threshold based on the consistency of non-edge configurations; this results in an increased capability to reject inconsistent edge candidates. The parameters of the image model can be robustly estimated from image-statistics. The approach endows the hysteresis linking algorithm with adaptive capabilities.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

CVPR Semantic Scholar

Cite

Text

Hancock and Kittler. "Adaptive Estimation of Hysteresis Thresholds." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991. doi:10.1109/CVPR.1991.139687

Markdown

[Hancock and Kittler. "Adaptive Estimation of Hysteresis Thresholds." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991.](https://mlanthology.org/cvpr/1991/hancock1991cvpr-adaptive/) doi:10.1109/CVPR.1991.139687

BibTeX

@inproceedings{hancock1991cvpr-adaptive,
  title     = {{Adaptive Estimation of Hysteresis Thresholds}},
  author    = {Hancock, Edwin R. and Kittler, Josef},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1991},
  pages     = {196-201},
  doi       = {10.1109/CVPR.1991.139687},
  url       = {https://mlanthology.org/cvpr/1991/hancock1991cvpr-adaptive/}
}