Steering in Scale Space to Optimally Detect Image Structures

  • Jeffrey Ng
  • Anil A. Bharath
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3021)


Detecting low-level image features such as edges and ridges with spatial filters is improved if the scale of the features are known a priori. Scale-space representations and wavelet pyramids address the problem by using filters over multiple scales. However, the scales of the filters are still fixed beforehand and the number of scales is limited by computational power. The filtering operations are thus not adapted to detect image structures at their optimal or intrinsic scales. We adopt the steering approach to obtain filter responses at arbitrary scales from a small set of filters at scales chosen to accurately sample the “scale space” within a given range. In particular, we use the Moore-Penrose inverse to learn the steering coefficients, which we then regress by polynomial function fitting to the scale parameter in order to steer the filter responses continuously across scales. We show that the extrema of the polynomial steering functions can be easily computed to detect interesting features such as phase-independent energy maxima. Such points of energy maxima in our α-scale-space correspond to the intrinsic scale of the filtered image structures. We apply the technique to several well-known images to segment image structures which are mostly characterised by their intrinsic scale.


Energy Maximum Image Structure Scale Space Radial Frequency Scale Selection 
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.
    Simoncelli, E., Freeman, W.: The steerable pyramid: A flexible architecture for multi-scale derivative computation. In: IEEE Second International Conference on Image Processing (1995)Google Scholar
  2. 2.
    Fdez-Valdivia, J., Garcia, J., Martinez-Baena, J., Fdez-Vidal, X.: The selection of natural scales in 2d images using adaptive Gabor filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 458–469 (1998)CrossRefGoogle Scholar
  3. 3.
    Lindeberg, T.: Principles for automatic scale selection. In: Handbook on Computer Vision and Applications, vol. 2, pp. 239–274. Academic Press, London (1999)Google Scholar
  4. 4.
    Kadir, T., Brady, M.: Scale, saliency and image description. International Journal of Computer Vision 45, 83–105 (2001)zbMATHCrossRefGoogle Scholar
  5. 5.
    Bredfelt, C., Ringach, D.: Dynamics of spatial frequency tuning in macaque v1. Journal of Neuroscience 22, 1976–1984 (2002)Google Scholar
  6. 6.
    Lindeberg, T., Bretzner, L.: Real-time scale selection in hybrid multi-scale representations. In: Griffin, L.D., Lillholm, M. (eds.) Scale-Space 2003. LNCS, vol. 2695, Springer, Heidelberg (2003)CrossRefGoogle Scholar
  7. 7.
    Crowley, J., Riff, O.: Fast computation of scale normalised gaussian receptive fields. In: Griffin, L.D., Lillholm, M. (eds.) Scale-Space 2003. LNCS, vol. 2695, pp. 584–598. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  8. 8.
    Freeman, W.T., Adelson, E.H.: The design and use of steerable filters. IEEE Transactions on Pattern Analysis and Machine Intelligence 13, 891–906 (1991)CrossRefGoogle Scholar
  9. 9.
    Perona, P.: Deformable kernels for early vision. IEEE Transactions on Pattern Analysis and Machine Intelligence 17, 488–499 (1995)CrossRefGoogle Scholar
  10. 10.
    Bharath, A.A.: Scale steerability of a class of digital filters. Electronics Letters 34, 1087–1088 (1998)CrossRefGoogle Scholar
  11. 11.
    Granlund, G., Knutsson, H.: Signal Processing for Computer Vision. Kluwer Academic Publishers, Dordrecht (1994)Google Scholar
  12. 12.
    Witkin, A., Terzopoulos, D., Kass, M.: Signal matching through scale space. International Journal of Computer Vision 1, 133–144 (1987)CrossRefGoogle Scholar
  13. 13.
    Duits, R., Felsberg, M., Florack, L., Platel, B.: α scale spaces on a bounded domain. In: Griffin, L.D., Lillholm, M. (eds.) Scale-Space 2003. LNCS, vol. 2695, pp. 494–510. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  14. 14.
    Papoulis, A.: Probability, Random Variables and Stochastic Processes. McGraw-Hill, New York (1984)zbMATHGoogle Scholar
  15. 15.
    Bharath, A.: Steerable filters from Erlang functions. In: British Machine Vision Conference, vol. 1, pp. 144–153 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Jeffrey Ng
    • 1
  • Anil A. Bharath
    • 1
  1. 1.Faculty of EngineeringImperial College LondonUnited Kingdom

Personalised recommendations