ML Anthology

From Contours to Regions: An Empirical Evaluation

Pablo Arbeláez, Michael Maire, Charless C. Fowlkes, Jitendra Malik
CVPR 2009 pp. 2294-2301
doi:10.1109/CVPR.2009.5206707 /cvpr/2009/arbelaez2009cvpr-contours/

Abstract

We propose a generic grouping algorithm that constructs a hierarchy of regions from the output of any contour detector. Our method consists of two steps, an oriented watershed transform (OWT) to form initial regions from contours, followed by construction of an ultra-metric contour map (UCM) defining a hierarchical segmentation. We provide extensive experimental evaluation to demonstrate that, when coupled to a high-performance contour detector, the OWT-UCM algorithm produces state-of-the-art image segmentations. These hierarchical segmentations can optionally be further refined by user-specified annotations.

PDF CVPR Semantic Scholar

Cite

Text

Arbeláez et al. "From Contours to Regions: An Empirical Evaluation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009. doi:10.1109/CVPR.2009.5206707

Markdown

[Arbeláez et al. "From Contours to Regions: An Empirical Evaluation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009.](https://mlanthology.org/cvpr/2009/arbelaez2009cvpr-contours/) doi:10.1109/CVPR.2009.5206707

BibTeX

@inproceedings{arbelaez2009cvpr-contours,
  title     = {{From Contours to Regions: An Empirical Evaluation}},
  author    = {Arbeláez, Pablo and Maire, Michael and Fowlkes, Charless C. and Malik, Jitendra},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2009},
  pages     = {2294-2301},
  doi       = {10.1109/CVPR.2009.5206707},
  url       = {https://mlanthology.org/cvpr/2009/arbelaez2009cvpr-contours/}
}