ML Anthology

A Bayesian Multiple Hypothesis Approach to Contour Grouping

Ingemar J. Cox, James M. Rehg, Sunita L. Hingorani
ECCV 1992 pp. 72-77
doi:10.1007/3-540-55426-2_9 /eccv/1992/cox1992eccv-bayesian/

Abstract

We present an approach to contour grouping based on classical tracking techniques. Edge points are segmented into smooth curves so as to minimize a recursively updated Bayesian probability measure. The resulting algorithm employs local smoothness constraints and a statistical description of edge detection, and can accurately handle corners, bifurcations, and curve intersections. Experimental results demonstrate good performance.

PDF ECCV Semantic Scholar

Cite

Text

Cox et al. "A Bayesian Multiple Hypothesis Approach to Contour Grouping." European Conference on Computer Vision, 1992. doi:10.1007/3-540-55426-2_9

Markdown

[Cox et al. "A Bayesian Multiple Hypothesis Approach to Contour Grouping." European Conference on Computer Vision, 1992.](https://mlanthology.org/eccv/1992/cox1992eccv-bayesian/) doi:10.1007/3-540-55426-2_9

BibTeX

@inproceedings{cox1992eccv-bayesian,
  title     = {{A Bayesian Multiple Hypothesis Approach to Contour Grouping}},
  author    = {Cox, Ingemar J. and Rehg, James M. and Hingorani, Sunita L.},
  booktitle = {European Conference on Computer Vision},
  year      = {1992},
  pages     = {72-77},
  doi       = {10.1007/3-540-55426-2_9},
  url       = {https://mlanthology.org/eccv/1992/cox1992eccv-bayesian/}
}