Early Jump-Out Corner Detectors

Abstract

Two corner detectors are presented, one of which works by testing similarity of image patches along the contour direction to detect curves in the image contour, and the other of which uses direct estimation image curvature along the contour direction. The operators are fast, robust to noise, and self-thresholding. An interpretation of the Kitchen-Rosenfeld corner operator is presented which shows that this operator can also be viewed as the second derivative of the image function along the edge direction.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Cite

Text

Cooper et al. "Early Jump-Out Corner Detectors." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991. doi:10.1109/CVPR.1991.139783

Markdown

[Cooper et al. "Early Jump-Out Corner Detectors." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991.](https://mlanthology.org/cvpr/1991/cooper1991cvpr-early/) doi:10.1109/CVPR.1991.139783

BibTeX

@inproceedings{cooper1991cvpr-early,
  title     = {{Early Jump-Out Corner Detectors}},
  author    = {Cooper, James W. and Venkatesh, Svetha and Kitchen, Leslie J.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1991},
  pages     = {688-689},
  doi       = {10.1109/CVPR.1991.139783},
  url       = {https://mlanthology.org/cvpr/1991/cooper1991cvpr-early/}
}