ML Anthology

A Hierarchical Approach to High Resolution Edge Contour Reconstruction

Stefano Casadei, Sanjoy K. Mitter
CVPR 1996 pp. 149-154
doi:10.1109/CVPR.1996.517067 /cvpr/1996/casadei1996cvpr-hierarchical/

Abstract

Efficient edge detection algorithms such as Canny's (1986) fail near curve singularities. Moreover, the standard linking algorithms used on top of these detectors often fail because of instabilities in the tracking process (due to multiple responses to the same edge and interference of nearby edges). We propose a hierarchical approach to edge detection based on a graph stabilization method that allows bifurcation resolution in stages. Curve singularities are recovered at the last stage by using "top-down" feedback to select the best curve connections.

CVPR Semantic Scholar

Cite

Text

Casadei and Mitter. "A Hierarchical Approach to High Resolution Edge Contour Reconstruction." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996. doi:10.1109/CVPR.1996.517067

Markdown

[Casadei and Mitter. "A Hierarchical Approach to High Resolution Edge Contour Reconstruction." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996.](https://mlanthology.org/cvpr/1996/casadei1996cvpr-hierarchical/) doi:10.1109/CVPR.1996.517067

BibTeX

@inproceedings{casadei1996cvpr-hierarchical,
  title     = {{A Hierarchical Approach to High Resolution Edge Contour Reconstruction}},
  author    = {Casadei, Stefano and Mitter, Sanjoy K.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1996},
  pages     = {149-154},
  doi       = {10.1109/CVPR.1996.517067},
  url       = {https://mlanthology.org/cvpr/1996/casadei1996cvpr-hierarchical/}
}