ML Anthology

Shape Representation and Recognition from Curvature

Gregory Dudek, John K. Tsotsos
CVPR 1991 pp. 35-41
doi:10.1109/CVPR.1991.139657 /cvpr/1991/dudek1991cvpr-shape/

Abstract

An approach for describing objects for the purpose of recognition is developed. The authors deal with two key issues: building natural descriptions of curved objects, and making these descriptions compact and abstract. Typical examples of the types of curve one is able to describe as both qualitatively similar, yet discriminably different, are shown. Methods based on curvature extrema alone are likely to find three of the four of these shapes indistinguishable, while methods based on approaches such as shape templates may be oblivious to their similarity. The central ideas of the approach are outlined.< <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

Dudek and Tsotsos. "Shape Representation and Recognition from Curvature." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991. doi:10.1109/CVPR.1991.139657

Markdown

[Dudek and Tsotsos. "Shape Representation and Recognition from Curvature." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991.](https://mlanthology.org/cvpr/1991/dudek1991cvpr-shape/) doi:10.1109/CVPR.1991.139657

BibTeX

@inproceedings{dudek1991cvpr-shape,
  title     = {{Shape Representation and Recognition from Curvature}},
  author    = {Dudek, Gregory and Tsotsos, John K.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1991},
  pages     = {35-41},
  doi       = {10.1109/CVPR.1991.139657},
  url       = {https://mlanthology.org/cvpr/1991/dudek1991cvpr-shape/}
}