From Contours to Regions: An Empirical Evaluation
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 Ultrametric 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.
Download: pdf
Text Reference
Pablo Arbelaez, Michael Maire, Charless C. Fowlkes, and Jitendra Malik. From contours to regions: an empirical evaluation. In CVPR. 2009.BibTeX Reference
@inproceedings{ArbelaezMFM_CVPR_2009,AUTHOR = "Arbelaez, Pablo and Maire, Michael and Fowlkes, Charless C. and Malik, Jitendra",
TITLE = "From Contours to Regions: An Empirical Evaluation",
BOOKTITLE = "CVPR",
YEAR = "2009",
TAG = "grouping"
}