The Role of Key-Points in Finding Contours

Abstract

This paper describes a method for aggregating local edge evidences into coherent pieces of contour. An independent representation of corner and junction features provides suitable stop-conditions for the aggregation process and allows to divide contours into meaningful substrings, right from the beginning. The active role of corner and junction points makes the Contours converge onto them and greatly reduces the problems associated with purely edge-based methods. A second stage is concerned with completing established contours across regions that are less well-defined by contrast. The algorithm suggested uses the attributes of established structures (e.g. direction of termination) as well as local orientation and edge evidences to constrain possible completions in a rigorous way.

Cite

Text

Henricsson and Heitger. "The Role of Key-Points in Finding Contours." European Conference on Computer Vision, 1994. doi:10.1007/BFB0028369

Markdown

[Henricsson and Heitger. "The Role of Key-Points in Finding Contours." European Conference on Computer Vision, 1994.](https://mlanthology.org/eccv/1994/henricsson1994eccv-role/) doi:10.1007/BFB0028369

BibTeX

@inproceedings{henricsson1994eccv-role,
  title     = {{The Role of Key-Points in Finding Contours}},
  author    = {Henricsson, Olof and Heitger, Friedrich},
  booktitle = {European Conference on Computer Vision},
  year      = {1994},
  pages     = {371-382},
  doi       = {10.1007/BFB0028369},
  url       = {https://mlanthology.org/eccv/1994/henricsson1994eccv-role/}
}