Image Specific Feature Similarities

  • Ido Omer
  • Michael Werman
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3952)


Calculating a reliable similarity measure between pixel features is essential for many computer vision and image processing applications. We propose a similarity measure (affinity) between pixel features, which depends on the feature space histogram of the image. We use the observation that clusters in the feature space histogram are typically smooth and roughly convex. Given two feature points we adjust their similarity according to the bottleneck in the histogram values on the straight line between them. We call our new similarities Bottleneck Affinities. These measures are computed efficiently, we demonstrate superior segmentation results compared to the use of the Euclidean metric.


Feature Space Feature Point Image Segmentation Texture Feature Segmentation Result 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Cheng, H.D., Jiang, X., Sun, Y., Wang, J.: Color image segmentation: advances and prospects. Pattern Recognition 34, 2259–2281 (2001)CrossRefzbMATHGoogle Scholar
  2. 2.
    Tuceryan, M., Jain, A.K.: Texture analysis, pp. 235–276 (1993)Google Scholar
  3. 3.
    Fowlkes, C., Martin, D., Malik, J.: Learning affinity functions for image segmentation: Combining patch-based and gradient-based approaches. In: Computer Vision and Pattern Recognition, CVPR (2003)Google Scholar
  4. 4.
    Comaniciu, D., Meer, P.: Robust analysis of feature spaces: color image segmentation. In: CVPR 1997: Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR 1997), vol. 750, p. 750. IEEE Computer Society, Washington, DC, USA (1997)Google Scholar
  5. 5.
    Mumford, D., Shah, J.: Boundary detection by minimizing functionals, I. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 22–26 (1985)Google Scholar
  6. 6.
    Vese, L.A., Chan, T.F.: A multiphase level set framework for image segmentation using the mumford and shah model. International Journal of Computer Vision 50, 271–293 (2002)CrossRefzbMATHGoogle Scholar
  7. 7.
    Spokoiny, V.: Estimation of a function with discontinuities via local polynomial fit with an adaptive window choice. Annals of Statistics, 1356–1378 (1998)Google Scholar
  8. 8.
    Gevers, T., Smeulders, A.W.M.: Color-based object recognition. Pattern Recognition 32, 453–464 (1999)CrossRefGoogle Scholar
  9. 9.
    Park, S., Schowengerdt, R.: Image sampling, reconstruction, and the effect of sample scene phasing. Applied Optics 21, 3142–3151 (1982)CrossRefGoogle Scholar
  10. 10.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI (2000)Google Scholar
  11. 11.
    Comaniciu, D., Meer, P.: Mean shift analysis and applications. In: ICCV 1999: Proceedings of the International Conference on Computer Vision, vol. 2, p. 1197. IEEE Computer Society, Washington, DC, USA (1999)Google Scholar
  12. 12.
    Leung, T., Malik, J.: Representing and recognizing the visual appearance of materials using three-dimensional textons. Int. J. Comput. Vision 43, 29–44 (2001)CrossRefzbMATHGoogle Scholar
  13. 13.
    Schmid, C.: Constructing models for content-based image retrieval. In: International Conference on Computer Vision & Pattern Recognition (2001)Google Scholar
  14. 14.
    Visual Geometry Group, University of Oxford,

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ido Omer
    • 1
  • Michael Werman
    • 1
  1. 1.School of Computer ScienceThe Hebrew University of JerusalemJerusalemIsrael

Personalised recommendations