Advertisement

A performance evaluation protocol for graphics recognition systems

  • Ihsin T. Phillips
  • Jisheng Liang
  • Atul K. Chhabra
  • Robert Haralick
Performance Evaluation
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1389)

Abstract

This paper defines a computational protocol for evaluating the performance of raster to vector conversion systems. The graphical entities handled by this protocol are continuous and dashed lines, arcs, and circles, and text regions. The protocol allows matches of the type one-to-one, one-to-many, and many-to-one between the ground truth and the recognition results.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    B. Kong, I. Phillips, R. Haralick, A. Prasad, and R. Kasturi. A benchmark: Performance evaluation of dashed line detection algorithms. In R. Kasturi and K. Tombre, editors, Graphics Recognition: Methods and Applications, First International Workshop, University Park, PA, USA, August 1995, Selected Papers, volume 1072 of Lecture Notes in Computer Science, pages 270–285. Springer, Berlin, 1996.Google Scholar
  2. 2.
    ECVNet. Benchmarking and Performance Evaluation web site. http://pandora.imag.fr/ECVNet/benchmarking.html.Google Scholar
  3. 3.
    O. Hori and S. Doermann. Quantitative measurement of the performance of rasterto-vector conversion algorithms. In R. Kasturi and K. Tombre, editors, Graphics Recognition: Methods and Applications, First International Workshop, University Park, PA, USA, August 1995, Selected Papers, volume 1072 of Lecture Notes in Computer Science, pages 57–68. Springer, Berlin, 1996.Google Scholar
  4. 4.
    L. Wenyin and D. Dori. A protocol for performance evaluation of line detection algorithms. Machine Vision and Applications, 9(5/6):240–250, 1997. Special Issue on Performance Char act erisitics of Vision Algorithms.Google Scholar
  5. 5.
    L. Wenyin and D. Dori. A protocol for performance evaluation of algorithms for text segmentation from graphics-rich documents. In Proceedings of Second IAPR Workshop on Graphics Recognition, pages 317–324, Nancy, France, August 1997.Google Scholar
  6. 6.
    R. Haralick. Performance characterization in image analysis: Thinning, a case in point. Pattern Recognition Letters, 13:5–12, 1992.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Ihsin T. Phillips
    • 1
  • Jisheng Liang
    • 2
  • Atul K. Chhabra
    • 3
  • Robert Haralick
    • 2
  1. 1.Department of Computer Science/Software EngineeringSeattle UniversitySeattle
  2. 2.Department of Electrical EngineeringUniversity of WashingtonSeattle
  3. 3.Bell Atlantic Network Systems, Advanced TechnologyWhite PlainsUSA

Personalised recommendations