Advertisement

International Journal of Computer Vision

, Volume 85, Issue 2, pp 167–181 | Cite as

Benchmarking Image Segmentation Algorithms

  • Francisco J. Estrada
  • Allan D. Jepson
Article

Abstract

We present a thorough quantitative evaluation of four image segmentation algorithms on images from the Berkeley Segmentation Database. The algorithms are evaluated using an efficient algorithm for computing precision and recall with regard to human ground-truth boundaries. We test each segmentation method over a representative set of input parameters, and present tuning curves that fully characterize algorithm performance over the complete image database. We complement the evaluation on the BSD with segmentation results on synthetic images. The results reported here provide a useful benchmark for current and future research efforts in image segmentation.

Keywords

Computer vision Image segmentation Quantitative evaluation Boundary matching 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Belongie, S., & Malik, J. (1998). Finding boundaries in natural images: A new method using point descriptors and area completion. In European conference on computer vision (pp. 751–766). Google Scholar
  2. Belongie, S., Fowlkes, C., Chung, F., & Malik, J. (2002). Spectral partitioning with indefinite kernels using the Nyström extension. In European conference on computer vision (pp. 21–31). Google Scholar
  3. Blake, A., Rother, A., Brown, M., Perez, P., & Torr, P. (2004). Interactive image segmentation using an adaptive GMMRF model. In European conference on computer vision (pp. 428–441). Google Scholar
  4. Borra, S., & Sarkar, S. (1997). A framework for performance characterization of intermediate-level grouping modules. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(11), 1306–1312. CrossRefGoogle Scholar
  5. Boykov, Y. Y., & Jolly, M.-P. (2001). Interactive Graph Cuts for optimal boundary & region segmentation of objects in N-D images. In IEEE international conference on computer vision (pp. 105–112). Google Scholar
  6. Boykov, Y., & Kolmogorov, V. (2001). An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. In International workshop on energy minimization methods in computer vision and pattern recognition. Lecture Notes in Computer Science (pp. 359–374). Google Scholar
  7. Boykov, Y., Veksler, O., & Zabih, R. (2001). Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(11), 1222–1239. CrossRefGoogle Scholar
  8. Cheng, Y. (1995). Mean shift, mode seeking, and clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(8), 790–799. CrossRefGoogle Scholar
  9. Cho, K., & Meer, P. (1997). Image segmentation from consensus information. Computer Vision and Image Understanding, 68(1), 72–89. CrossRefGoogle Scholar
  10. Comaniciu, D., & Meer, P. (2002). Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5), 603–619. CrossRefGoogle Scholar
  11. Cour, T., Yu, S., & Shi, J. (2006). Normalized cuts Matlab code. Computer and Information Science, Penn State University. code available at http://www.seas.upenn.edu/~timothee/software_ncut/software.html.
  12. Estrada, F. J. (2005). Advances in computational image segmentation and perceptual grouping. PhD thesis, University of Toronto, Department of Computer Science. Google Scholar
  13. Estrada, F. J., & Jepson, A. D. (2004). Spectral embedding and min-cut for image segmentation. In British machine vision conference (pp. 317–326). Google Scholar
  14. Estrada, F. J., & Jepson, A. D. (2005). Quantitative evaluation of a novel image segmentation algorithm. In IEEE international conference on computer vision and pattern recognition. Google Scholar
  15. Felzenszwalb, P., & Huttenlocher, D. (2004). Image segmentation by local variation code. MIT Artificial Intelligence Lab. Code available at http://people.cs.uchicago.edu/~pff/segment/.
  16. Felzenszwalb, P. F., & Huttenlocher, D. P. (1998). Image segmentation using local variation. In IEEE conference on computer vision and pattern recognition (pp. 98–104). Google Scholar
  17. Fowlkes, C., Belongie, S., & Malik, J. (2001). Efficient spatiotemporal grouping using the Nyström method. In IEEE conference on computer vision and pattern recognition (pp. 231–238). Google Scholar
  18. Fowlkes, C., Belongie, S., Chung, F., & Malik, J. (2004). Spectral grouping using the Nyström method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(2), 214–225. CrossRefGoogle Scholar
  19. Gdalyahu, Y., Weinshall, D., & Werman, M. (2001). Self-organization in vision: Stochastic clustering for image segmentation, perceptual grouping, and image database organization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(10), 1053–1074. CrossRefGoogle Scholar
  20. Georgescu, B., & Christoudias, C. M. (2003). The Edge Detection and Image segmentation (EDISON) system. Robust Image Understanding Laboratory, Rutgers University. Code available at http://web.archive.org/web/20060617020918/www.caip.rutgers.edu/riul/research/code/EDISON/index.html.
  21. Ishikawa, H., & Geiger, D. (1998). Segmentation by grouping junctions. In IEEE conference on computer vision and pattern recognition (pp. 125–131). Google Scholar
  22. Kaufhold, J., & Hoogs, A. (2004). Learning to segment images using region-based perceptual properties. In IEEE international conference on computer vision and pattern recognition (vol. 2, pp. 954–961). Google Scholar
  23. Malik, J., Belongie, S., Leung, T., & Shi, J. (1999). Textons, contours and regions: Cue integration in image segmentation. In IEEE international conference on computer vision (pp. 918–925). Google Scholar
  24. Malik, J., Belongie, S., Leung, T., & Shi, J. (2001). Contour and texture analysis for image segmentation. International Journal of Computer Vision, 43(1), 7–27. zbMATHCrossRefGoogle Scholar
  25. Martin, D. (2002). An empirical approach to grouping and segmentation. PhD thesis, University of California, Berkeley. Google Scholar
  26. Martin, D., & Fowlkes, C. (2001). The Berkeley segmentation database and benchmark. Computer Science Department, Berkeley University. http://www.eecs.berkeley.edu/Research/Projects/CS/vision/bsds/.
  27. Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2001). A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In IEEE international conference on computer vision (pp. 416–425). Google Scholar
  28. Martin, D. R., Fowlkes, C. C., & Malik, J. (2002). Learning to detect natural image boundaries using brightness and texture. In Neural information processing systems. Google Scholar
  29. Martin, D., Fowlkes, C., & Malik, J. (2004). Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(5), 530–549. CrossRefGoogle Scholar
  30. Meila, M., & Shi, J. (2000). Learning segmentation by random walks. In NIPS (pp. 873–879). Google Scholar
  31. Sharon, E., Brandt, A., & Basri, R. (2000). Fast multiscale image segmentation. In IEEE conference on computer vision and pattern recognition (pp. 70–77). Google Scholar
  32. Sharon, E., Brandt, A., & Basri, R. (2001). Segmentation and boundary detection using multiscale intensity measurements. In IEEE conference on computer vision and pattern recognition (pp. 469–476). Google Scholar
  33. Shental, N., Zomet, A., Hertz, T., & Weiss, Y. (2003). Learning and inferring image segmentations using the GBP typical cut algorithm. In IEEE international conference on computer vision (pp. 1243–1250). Google Scholar
  34. Shi, J., & Malik, J. (2000). Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8), 888–905. CrossRefGoogle Scholar
  35. Veksler, O. (2000). Image segmentation by nested cuts. In IEEE conference on computer vision and pattern recognition (pp. 339–344). Google Scholar
  36. Wang, S., & Siskind, J. M. (2001). Image segmentation with minimum mean cut. In IEEE international conference on computer vision (pp. 517–524). Google Scholar
  37. Wang, S., & Siskind, J. M. (2003). Image segmentation with ratio cut. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(6), 675–690. CrossRefGoogle Scholar
  38. Wu, Z., & Leahy, R. (1993). An optimal graph theoretic approach to data clustering: Theory and its application to image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(11), 1101–1113. CrossRefGoogle Scholar
  39. Yu, S. X. (2004). Segmentation using multiscale cues. In IEEE international conference on computer vision and pattern recognition (pp. 247–254). Google Scholar
  40. Yu, S. X. (2005). Segmentation induced by scale invariance. In IEEE international conference on computer vision and pattern recognition. Google Scholar
  41. Yu, S. X., & Shi, J. (2003). Multiclass spectral clustering. In IEEE International Conference on Computer Vision (pp. 313–319). Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of TorontoTorontoCanada

Personalised recommendations