Detection of General Edges and Keypoints

Abstract

A computational framework for extracting (1) edges with an arbitrary profile function and (2) keypoints such as corners, vertices and terminations is presented. Using oriented filters with even and odd symmetry we combine their convolution outputs to oriented energy resulting in a unified representation of edges, lines and combinations thereof. We derive an ” edge quality” measure which allows to test the validity of a general edge model. A detection scheme for keypoints is proposed based on an analysis of oriented energy channels using differential geometry.

Cite

Text

Rosenthaler et al. "Detection of General Edges and Keypoints." European Conference on Computer Vision, 1992. doi:10.1007/3-540-55426-2_10

Markdown

[Rosenthaler et al. "Detection of General Edges and Keypoints." European Conference on Computer Vision, 1992.](https://mlanthology.org/eccv/1992/rosenthaler1992eccv-detection/) doi:10.1007/3-540-55426-2_10

BibTeX

@inproceedings{rosenthaler1992eccv-detection,
  title     = {{Detection of General Edges and Keypoints}},
  author    = {Rosenthaler, Lukas and Heitger, Friedrich and Kübler, Olaf and von der Heydt, Rüdiger},
  booktitle = {European Conference on Computer Vision},
  year      = {1992},
  pages     = {78-86},
  doi       = {10.1007/3-540-55426-2_10},
  url       = {https://mlanthology.org/eccv/1992/rosenthaler1992eccv-detection/}
}