How the Spatial Filters of Area V1 Can Be Used for a Nearly Ideal Edge Detection

  • Felice Andrea Pellegrino
  • Walter Vanzella
  • Vincent Torre
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2525)


The present manuscript aims to address and possibly solve three classical problems of edge detection: i—the detection of all step edges from a fine to a coarse scale; ii—the detection of thin bars, i.e. of roof edges; iii—the detection of corners and trihedral junctions. The proposed solution of these problems combines an extensive spatial filtering, inspired by the receptive field properties of neurons in the visual area V1, with classical methods of Computer Vision (Morrone & Burr 1988; Lindeberg 1998; Kovesi 1999) and newly developed algorithms. Step edges are computed by extracting local maxima from the energy summed over a large bank of odd filters of different scale and direction. Thin roof edges are computed by considering maxima of the energy summed over narrow odd and even filters along the direction of maximal response. Junctions are precisely detected by an appropriate combination of the output of directional filters. Detected roof edges are cleaned by using a regularization procedure and are combined with step edges and junctions in a Mumford-Shah type functional with self adaptive parameters, providing a nearly ideal edge detection and segmentation.


Edge Detection Visual Area Coarse Scale Spatial Filter Step Edge 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Alvarez L., P.-L. Lions, Morel, “Image selective smoothing and edge detection by nonlinear diffusion”, “SIAM Journal on numerical analysis”, pp. 845–866, 1992Google Scholar
  2. Anderson S.J. and Burr D.C., “Spatial summation properties of directionally selective mechanisms in human vision”J. Opt Soc Am A., Vol.8, No.8, pp.1330–9, 1991CrossRefGoogle Scholar
  3. Anderson S.J. and Burr D.C. “Receptive field properties of human motion detector units inferred from spatial frequency masking”, Vision Res., Vol.29, No.10, pp.1343–58,1989CrossRefGoogle Scholar
  4. Beaudet P.R., “Rotational invariant image operators”, in Int. Conference on Pattern Recognition, pp. 579–583,1978Google Scholar
  5. Blakemore, C. and Campbell, F.W. “On the existence of neurones in the visual system selectively sensitive to the orientation and size of retinal images”, J. Physiol. (London), No.225,pp.437–455, 1969Google Scholar
  6. Brunnstrom K., Lindeberg T., Eklundh J.O., “Active detection and classification of junctions”, Proc. of the Second European Conference on Computer Vision, Vol. LNCS 588, St. Margherita Ligure, Italy, pp. 701–709, 1992Google Scholar
  7. Burr D. and Morrone M.C., “A nonlinear model of feature detection”, in Nonlinear Vision, Determination of Receptive Field, Function and Networks, CRC Press, Boca Raton, Florida, 1992Google Scholar
  8. Canny, J.F. “A Computational Approach to Edge Detection”, IEEE Transanctions on Pattern Analysis and Machine Intelligence, No.8, pp.679–698,1986Google Scholar
  9. Deriche R. and Giraudon G., “A Computational Approach to for Corner and Vertex Detection” International Journal on Computer Vision, Vol.10, No.2 pp. 102–124, 1993CrossRefGoogle Scholar
  10. Dreschler L., Nagel H.H., “On the selection of critical points and local curvature extrema of region boundaries for interframe matching”, in Int. Conference on Pattern Recognition, pp. 542–544, 1982Google Scholar
  11. Field D.J. and Tolhurst, D.J. “The structure and symmetry of simple-cell receptive field profiles in the cat’s visual cortex”, Proc. R. Soc. London B, No.228, 379–399, 1986Google Scholar
  12. Freeman W.T. and Adelson E.H., “The design and use of steerable filters”, IEEE Trans. on PAMI, Vol.13, No.9, pp.891–906, 1991CrossRefGoogle Scholar
  13. Freeman W.T., “Steereable Filters and Local Analysis of Image Structures”, Ph.D. Thesis, MIT 1992Google Scholar
  14. Grossberg S., Raizada R., “Contrast-Sensitive perceptual grouping and object-based attention in the laminar circuits of primary visual cortex”, Tech. Rep. CAS/CNS TR 99-008, 1999Google Scholar
  15. Grossberg S., Gove A., Mingolla E. “Brightness, perception, illusory contours an corticogeniculate feedback”, Journal of Vision Neuroscience, 12 pp. 1027–1052, 1995CrossRefGoogle Scholar
  16. Grossman A. “Wavelet transforms and edge detection”, in Albeverio S., Blanchard P., Hezewinkel M. and Streit L. (eds)Stochastic Processes in Physics and Engineering, pp.149–157, Reidel Publishing Company, 1988Google Scholar
  17. Hansen T., Neumann H., “Neural Mechanisms for Representing Surface and Contour Features”, Emergent Neural Computational Architectures, LNAI, pp. 139–153, 2001Google Scholar
  18. Heeger D.J., “Normalization of cell responses in cat striate cortex”, Visual Neuroscience, No.9, pp.181–197, 1992Google Scholar
  19. Hegde, J. and Van Essen, D.C., “Selectivity for complex shapes in primate visual area V2”, J. Neurosci. 20:RC, pp. 61–66., 2000Google Scholar
  20. Hubel, D. H. and Wiesel, T. N. “Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) of the cat”, Journal of Neurophysiology, No.28, pp.229–289, 1965Google Scholar
  21. Kitchen L. e Rosenfeld A., “Gray-level corner detection”, Pattern Recognition Letters, Vol.1, No.2, pp.95–102, 1982CrossRefGoogle Scholar
  22. Kovesi P. “Image Features from Phase Congruency”, Videre, Vol.1, No.3, pp.1–26, MIT Press, 1999Google Scholar
  23. Lindeberg T., “Edge detection and ridge detection with automatic scale selection”, International Journal of Computer Vision, Vol.30, No.2, 1998Google Scholar
  24. Meyer Y., Wavelets—Algorithms and Applications, SIAM, 1993Google Scholar
  25. Morel J.M. and Solimini S., Variational Methods in Image Segmentation, Birkhäuser, 1995Google Scholar
  26. Morrone M.C. and Burr D., “Feature detection in human vision: a phase-dependent energy model”, Proc. Royal Society London B, No.235, pp.221–245, 1988Google Scholar
  27. Mumford D. and Shah J., ‘Optimal aproximation of Piecewise Smooth Function and associated variational problems’, Comm. in Pure and Appl. Math, No.42, pp.577–685, 1989Google Scholar
  28. Nordstrom N.K.,“Variational edge detection”, PhD Thesis, Univ. of California Berkeley,1992Google Scholar
  29. Pellegrino F.A., Vanzella W. and Torre V. “Edge Detection Revisited:Filtering”, 2003 in preparationGoogle Scholar
  30. Robbins B. and Owens R., “2D feature detection via local energy”, Image and Vision Computing, No.15, pp.353–368, 1997Google Scholar
  31. Ruzon M.A. and Tomasi C., “Edge, Junction, and Corner Detection Using Color Distributions”, IEEE Transactions on PAMI, Vol.23, No.11, pp.1281–1295, 2002CrossRefGoogle Scholar
  32. Simoncelli E. P. and Farid H., “Steerable wedge filters for local orientation analysis”, IEEE Trans. Image Processing, Vol.5, No.9, pp.1377–1382, 1996.CrossRefGoogle Scholar
  33. Torre V. and Poggio T.A. “On edge detection”, IEEE Trans. Pattern Anal. Mach. Intell., No.8, pp.148–163, 1986Google Scholar
  34. Vanzella W., Pellegrino F.A. and Torre V., “Edge Detection Revisited: Regularization”, 2003 in preparationGoogle Scholar
  35. Venkatesh S. and Owens R.A., “On the classification of image features”, Pattern Recognition Letters, No.11, pp.339–349, 1990Google Scholar
  36. Wilson H.R., McFarlane D.R. and Phillips G.C., “Spatial frequency tuning of orientation selective units estimated by oblique masking”, Vision Res., No.23, pp.873–882, 1983Google Scholar
  37. Witkin, A.,“ Scale-space filtering”, in Int. Joint Conf. on Artificial Intelligence, pp. 1019–1022, 1983Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Felice Andrea Pellegrino
    • 1
  • Walter Vanzella
    • 1
  • Vincent Torre
    • 1
  1. 1.INFM Unit and SISSATriesteItaly

Personalised recommendations