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 ultra-metric contour map (UCM) definin...

Full description

Saved in:
Bibliographic Details
Published in2009 IEEE Conference on Computer Vision and Pattern Recognition pp. 2294 - 2301
Main Authors Arbelaez, Pablo, Maire, Michael, Fowlkes, Charless, Malik, Jitendra
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2009
Subjects
Brightness
Detectors
Image edge detection
Image segmentation
Inference algorithms
Leak detection
Level set
Machinery
Object recognition
Pixel
Online AccessGet full text
ISBN1424439922
9781424439928
ISSN1063-6919
1063-6919
DOI10.1109/CVPR.2009.5206707

Cover

More Information
Summary: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.
ISBN:1424439922
9781424439928
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2009.5206707