A Formal Framework for the Objective Evaluation of Edge Detectors

@inproceedings{Dougherty1998AFF,
  title={A Formal Framework for the Objective Evaluation of Edge Detectors},
  author={Sean Dougherty and Kevin W. Bowyer},
  booktitle={FLAIRS Conference},
  year={1998}
}
Edge detection is one of the most-studied problems in the field of computer vision. However, there is no standard method of objectively and accurately evaluating the performance of an edge detector. This work proposes such a framework. The framework is based on using real images, hand-specified ground truth, and a receiver operating characteristic (ROC) curve style analysis of true positive and false positive edge pixels. The method is illustrated by developing a comparison of six edge… CONTINUE READING
Highly Cited
This paper has 23 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

References

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

Camera Models ~md Machine Po.rccption

  • I. E. Sobel
  • Stanford University,
  • 1970
Highly Influential
6 Excerpts

The FER:ET Evaluation Mettmdology for Face- Recognition Algorithms

  • P. J. Phillips, Moon, It, Patrick, S. Rizvi
  • Computer Vision and Pattern Recognition,
  • 1997
1 Excerpt

A methodology for cvahtating edge detection techniques for range images

  • X. Y. Jiang, et
  • Asian Conference on Computer Vision,
  • 1995

A methodology for evaluating edge detection techniques for razlge

  • X. Y. Jiang, A. Hoover, G Jean-Baptiste.., D. Goldgof, K. Bowyer, H. Bunke
  • Asian Conference on Computer Vision,
  • 1995
1 Excerpt

Using Optical Flow to Analyze the Motion of Human Body Organs from Bioimages

  • M. Tistarelli, G. Marcenaro
  • Proceedings of the IEEE Workshop on Biomedical…
  • 1994
1 Excerpt

Similar Papers

Loading similar papers…