From contours to regions: An empirical evaluation

Pablo Arbelaez, Michael Maire, Charless C. Fowlkes, Jitendra Malik

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.
BibTeX
@inproceedings{arbelaez2009from,
  author = {Pablo Arbelaez and Michael Maire and Charless C. Fowlkes and Jitendra Malik},
  title = {{From contours to regions: An empirical evaluation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2009},
  doi = {10.1109/cvpr.2009.5206707},
}

Loading related content...

Figure