ML Anthology

Finding Convex Edge Groupings in an Image

Daniel P. Huttenlocher, Peter C. Wayner
CVPR 1991 pp. 406-412
doi:10.1109/CVPR.1991.139724 /cvpr/1991/huttenlocher1991cvpr-finding/

Abstract

A method for identifying groups of intensity edges in an image that are likely to result from the same convex object in a scene is described. A key property of the method is that its output is no more complex than the original image. The method uses a triangulation of linear edge segments to define a local neighborhood that is scale invariant. From this local neighborhood a local convexity graph that encodes which neighboring image edges could be part of a convex group of image edges is constructed. A path in the graph corresponds to a convex polygonal chain in the image, such as a convex polygon or a spiral. Examples are presented to illustrate that the technique find intuitively salient groups.< <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

Huttenlocher and Wayner. "Finding Convex Edge Groupings in an Image." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991. doi:10.1109/CVPR.1991.139724

Markdown

[Huttenlocher and Wayner. "Finding Convex Edge Groupings in an Image." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991.](https://mlanthology.org/cvpr/1991/huttenlocher1991cvpr-finding/) doi:10.1109/CVPR.1991.139724

BibTeX

@inproceedings{huttenlocher1991cvpr-finding,
  title     = {{Finding Convex Edge Groupings in an Image}},
  author    = {Huttenlocher, Daniel P. and Wayner, Peter C.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1991},
  pages     = {406-412},
  doi       = {10.1109/CVPR.1991.139724},
  url       = {https://mlanthology.org/cvpr/1991/huttenlocher1991cvpr-finding/}
}