Describing and Matching 2D Shapes by Their Points of Mutual Symmetry

Abstract

A novel shape descriptor is introduced. It groups pairs of points that share a geometrical property that is based on their mutual symmetry. The descriptor is visualized as a diagonally symmetric diagram with binary valued regions. This diagram is a fingerprint of global symmetry between pairs of points along the shape. The descriptive power of the method is tested on a well-known shape data base containing several classes of shapes and partially occluded shapes. First tests with simple, elementary matching algorithms show good results.

Cite

Text

Kuijper and Olsen. "Describing and Matching 2D Shapes by Their Points of Mutual Symmetry." European Conference on Computer Vision, 2006. doi:10.1007/11744078_17

Markdown

[Kuijper and Olsen. "Describing and Matching 2D Shapes by Their Points of Mutual Symmetry." European Conference on Computer Vision, 2006.](https://mlanthology.org/eccv/2006/kuijper2006eccv-describing/) doi:10.1007/11744078_17

BibTeX

@inproceedings{kuijper2006eccv-describing,
  title     = {{Describing and Matching 2D Shapes by Their Points of Mutual Symmetry}},
  author    = {Kuijper, Arjan and Olsen, Ole Fogh},
  booktitle = {European Conference on Computer Vision},
  year      = {2006},
  pages     = {213-225},
  doi       = {10.1007/11744078_17},
  url       = {https://mlanthology.org/eccv/2006/kuijper2006eccv-describing/}
}