Contour Detection and Hierarchical Image Segmentation

  title={Contour Detection and Hierarchical Image Segmentation},
  author={Pablo Andr{\'e}s Arbel{\'a}ez and Michael Maire and Charless C. Fowlkes and Jitendra Malik},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
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… CONTINUE READING
Highly Influential
This paper has highly influenced 473 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 3,051 citations. REVIEW CITATIONS
1,757 Citations
74 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 1,757 extracted citations

3,051 Citations

Citations per Year
Semantic Scholar estimates that this publication has 3,051 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 74 references

Objective Criteria for the Evaluation of Clustering Methods

  • W. M. Rand
  • J. Am. Statistical Assoc., vol. 66, pp. 846-850…
  • 1971
Highly Influential
10 Excerpts

Similar Papers

Loading similar papers…