Contour Detection and Hierarchical Image Segmentation

  • Authors:
  • Pablo Arbelaez;Michael Maire;Charless Fowlkes;Jitendra Malik

  • Affiliations:
  • University of California at Berkeley, Berkeley;California Institute of Technology, Pasadena;University of California at Irvine, Irvine;University of California at Berkeley, Berkeley

  • Venue:
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Year:
  • 2011

Quantified Score

Hi-index 0.14

Visualization

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.