Format

Send to

Choose Destination
IEEE Trans Pattern Anal Mach Intell. 2011 May;33(5):898-916. doi: 10.1109/TPAMI.2010.161.

Contour detection and hierarchical image segmentation.

Author information

1
Department of Electrical Engineering and Computer Science, University of California at Berkeley, Berkeley, CA 94720, USA. arbelaez@eecs.berkeley.edu

Abstract

This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into a hierarchical region tree. In this manner, we reduce the problem of image segmentation to that of contour detection. Extensive experimental evaluation demonstrates that both our contour detection and segmentation methods significantly outperform competing algorithms. The automatically generated hierarchical segmentations can be interactively refined by user-specified annotations. Computation at multiple image resolutions provides a means of coupling our system to recognition applications.

PMID:
20733228
DOI:
10.1109/TPAMI.2010.161
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for IEEE Engineering in Medicine and Biology Society
Loading ...
Support Center