ML Anthology

Ridge's Corner Detection and Correspondence

Erez Shilat, Michael Werman, Yoram Gdalyahu
CVPR 1997 pp. 976-981
doi:10.1109/CVPR.1997.609446 /cvpr/1997/shilat1997cvpr-ridge/

Abstract

Traditionally, corners are found along step edges. In this paper we present an alternative approach-corners along ridges/troughs and local minima points. These features seem to be more reliable for tracking. A new approach for sub-pixel localization of these corners is suggested, using a local approximation of the image surface.

CVPR Semantic Scholar

Cite

Text

Shilat et al. "Ridge's Corner Detection and Correspondence." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609446

Markdown

[Shilat et al. "Ridge's Corner Detection and Correspondence." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/shilat1997cvpr-ridge/) doi:10.1109/CVPR.1997.609446

BibTeX

@inproceedings{shilat1997cvpr-ridge,
  title     = {{Ridge's Corner Detection and Correspondence}},
  author    = {Shilat, Erez and Werman, Michael and Gdalyahu, Yoram},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {976-981},
  doi       = {10.1109/CVPR.1997.609446},
  url       = {https://mlanthology.org/cvpr/1997/shilat1997cvpr-ridge/}
}