International Journal of Computer Vision

, Volume 11, Issue 3, pp 283–318

Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention

  • Tony Lindeberg
Article

Abstract

This article presents: (i) a multiscale representation of grey-level shape called the scale-space primal sketch, which makes explicit both features in scale-space and the relations between structures at different scales, (ii) a methodology for extracting significant blob-like image structures from this representation, and (iii) applications to edge detection, histogram analysis, and junction classification demonstrating how the proposed method can be used for guiding later-stage visual processes.

The representation gives a qualitative description of image structure, which allows for detection of stable scales and associated regions of interest in a solely bottom-up data-driven way. In other words, it generates coarse segmentation cues, and can hence be seen as preceding further processing, which can then be properly tuned. It is argued that once such information is available, many other processing tasks can become much simpler. Experiments on real imagery demonstrate that the proposed theory gives intuitive results.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    M. Abramowitz and I.A. Stegun, eds.,Handbook of Mathematical Functions. Applied Mathematics Series, National Bureau of Standards, 55 ed., 1964.Google Scholar
  2. 2.
    V.I. Arnold, S.M. Gusein-Zade, and A.N. Varchenko,Singularities of Smooth Maps, vol. I, Birkhäuser: Boston, 1985.Google Scholar
  3. 3.
    J. Babaud, A.P. Witkin, M. Baudin, and R.O. Duda, Uniqueness of the Guassian kernel for scale-space filtering,IEEE Trans. Patt. Anal. Mach. Intell. 8(1):26–33, 1986.Google Scholar
  4. 4.
    H.H. Baker, Surface reconstruction from image sequences,Proc. 2nd Intern. Conf. Comput. Vis. Tampa, FL, pp. 334–343, 1988.Google Scholar
  5. 5.
    F. Bergholm, Edge focusing,IEEE Trans. Patt. Anal. Mach. Intell. 9:726–741, November 1987.Google Scholar
  6. 6.
    I. Biederman, Human image understanding: Recent research and a theory, inHuman and Machine Vision II, Academic Press: San Diego, pp. 13–57, 1985.Google Scholar
  7. 7.
    F. Billmeyer and M. Saltzman,Principles of Colour Technology, Wiley: New York, 1982.Google Scholar
  8. 8.
    W.F. Bischof and T. Caelli, Parsing scale-space and spatial stability analysis,Comput. Vis. Graph. Image Process. 42:192–205, 1988.Google Scholar
  9. 9.
    J. Blom, Topological and Geometrical Aspects of Image Structure, Ph.D. thesis, Dept. Med. Phys. Physics, Univ. Utrecht, NL-3508 Utrecht, Netherlands, 1992.Google Scholar
  10. 10.
    D. Blostein and N. Ahuja, Shape from texture: integrating texture element extraction and surface estimation,IEEE Trans. Patt. Anal. Mach. Intell., 11:1233–1251, 1989.Google Scholar
  11. 11.
    K. Brunnström, J.O. Eklundh, and T. Lindeberg, Scale and resolution in active analysis of local image structure,Image Vis. Comput. 8:289–296, 1990.Google Scholar
  12. 12.
    K. Brunnström, T. Lindeberg, and J.O. Eklundh, Active detection and classification of junctions by foveation with a head-eye system guided by the scale-space primal sketch,Proc. 2nd Europ. Conf. Comput. Vis. Santa Margherita Ligure, Italy, May 1992. In G. Sandini, ed., vol. 588 ofLecture Notes in Computer Science, pp. 701–709, Springer-Verlag.Google Scholar
  13. 13.
    P.J. Burt, Fast filter transforms for image processing,Comput. Graphics, Image Proc. 16:20–51, 1981.Google Scholar
  14. 14.
    J. Canny, A computational approach to edge detection,IEEE Trans. Patt. Anal. Mach. Intell. 8(6):679–698, 1986.Google Scholar
  15. 15.
    M.J. Carlotto, Histogram analysis using a scale-space approach,IEEE Trans. Patt. Anal. Mach. Intell. 9:121–129, 1987.Google Scholar
  16. 16.
    J.L. Crowley and A.C. Parker, A representation for shape based on peaks and ridges in the Difference of Low-Pass Transform,IEEE Trans. Patt. Anal. Mach. Intell. 6(2):156–170, 1984.Google Scholar
  17. 17.
    J.L. Crowley and A.C. Sanderson, Multiple resolution representation and probabilistic matching of 2-D grey-scale shape,IEEE Trans. Patt. Anal. Mach. Intell., 9(1):113–121, 1987.Google Scholar
  18. 18.
    S.M. Culhane and J.K. Tsotsos, An attentional prototype for early vision,Proc. 2nd Europ. Conf. Comput. Vis., Santa Margherita Ligure, Italy, 1992, pp. 551–562.Google Scholar
  19. 19.
    S.J. Dickinson, A.P. Pendland, and A. Rosenfeld, “Qualitative 3-D reconstruction using distributed aspect graph matching,” inProc. 3rd Intern. Conf. Comput. Vis., Osaka, Japan, 1990, pp. 257–262.Google Scholar
  20. 20.
    R.W. Ehrich and P.F. Lai, Elements of a structural model of texture,Proc. PRIP, pp. 319–326, IEEE Computer Society Press: Los Alamitos, CA, 1978.Google Scholar
  21. 21.
    L.M.J. Florack, B.M. ter Haar Romeny, J.J. Koenderink, and M.A. Viergever, Scale and the differential structure of images,Image Vis. Comput. 10:376–388, 1992.Google Scholar
  22. 22.
    M.A. Förstner and E. Gulch, A fast operator for detection and precise location of distinct points, corners and centers of circular features, inISPRS Intercommission Workshop, 1987.Google Scholar
  23. 23.
    J. Gårding, Shape from surface markings. Ph.D. thesis, Dept. of Numerical Analysis and Computing Science, Royal Institute of Technology, Stockholm, 1991.Google Scholar
  24. 24.
    C.G. Gibson,Singular Points of Smooth Mappings, Research Notes in Mathematics, Pitman Publishing: London, 1979.Google Scholar
  25. 25.
    M. Golubitsky and D.G. Schaeffer,Singularities and Groups in Bifurcation Theory I, vol. 51 ofApplied Mathematical Sciences, Springer-Verlag: New York, 1985.Google Scholar
  26. 26.
    A.D. Gross, Multiresolution object detection and delineation, Tech. Rept. TR-1613, Computer Vision Laboratory, University of Maryland, 1986.Google Scholar
  27. 27.
    R.M. Haralick, L.T. Watson, and T.J. Laffey, The topographic primal sketch,Intern. J. Robotics Res. 2(1):50–72, 1983.Google Scholar
  28. 28.
    R. Hummel, The scale-space formulation of pyramid data structures,Parallel Computer Vision, L. Uhr, ed., pp. 187–223, Academic Press: New York, 1987.Google Scholar
  29. 29.
    P. Johansen, On the classification of toppoints in scale space,J. Math. Imag. Vis. (to appear), 1993.Google Scholar
  30. 30.
    B. Julesz and J.R. Bergen, Textons, the fundamental elements in preattentive vision and perception of textures,Bell Syst. Tech. J. 62(6):1619–1645, 1983.Google Scholar
  31. 31.
    M. Kass, A. Witkin, and D. Terzopoulos, Snakes: Active contour models,Intern. J. Comput. Vis. 1:321–331, 1987.Google Scholar
  32. 32.
    L. Kitchen and A. Rosenfeld, Gray-level corner detection,Patt. Recog. Lett. 1(2):95–102, 1982.Google Scholar
  33. 33.
    J.J. Koenderink, The structure of images,Biological Cybernetics 50:363–370, 1984.Google Scholar
  34. 34.
    J.J. Koenderink and A.J. van Doorn, Dynamic shape,Biological Cybernetics 53:383–396, 1986.Google Scholar
  35. 35.
    J.J. Koenderink and W. Richards, Two-dimensional curvature operators,J. Opt. Soc. Amer. 5(7):1136–1141, 1988.Google Scholar
  36. 36.
    J.J. Koenderink and A.J. van Doorn, Generic neighborhood operators,IEEE Trans. Patt. Anal. Mach. Intell. 14:597–605, June 1992.Google Scholar
  37. 37.
    D. Koller, K. Daniilides, T. Thórhallson, and H.-H. Nagel, Model-based object tracking in traffic scenes,Proc. 2nd Europ. Conf. Comput. Vis., Santa Margherita Ligure, Italy, 1992.Google Scholar
  38. 38.
    A.F. Korn, Toward a symbolic representation of intensity changes in images,IEEE Trans. Patt. Anal. Mach. Intell. 10(5):610–625, 1988.Google Scholar
  39. 39.
    M.D. Levine, Region analysis using a pyramid data structure. InStructured Computer Vision, S. Tanimoto and A. Klinger, eds., pp. 57–100, Academic Press: New York, 1980.Google Scholar
  40. 40.
    L.M. Lifshitz and S.M. Pizer, A multiresolution hierarchical approach to image segmentation based on intensity extrema,IEEE Trans. Patt. Anal. Mach. Intell. 12(6):529–541, 1990.Google Scholar
  41. 41.
    T. Lindeberg, Scale-space for discrete signals,IEEE Trans. Patt. Anal. Mach. Intell., 12:234–254, 1990.Google Scholar
  42. 42.
    T. Lindeberg and J.O. Eklundh, Scale detection and region extraction from a scale-space primal sketch,Proc. 3rd Intern. Conf. Comput. Vis., Osaka, Japan, pp. 416–426, December 1990.Google Scholar
  43. 43.
    T. Lindeberg, Discrete scale space theory and the scale space primal sketch, Ph.D. thesis, Dept. of Numerical Analysis and Computing Science, Royal Institute of Technology, Stockholm, May 1991. A revised and extended version to appear as bookScale-Space Theory in Early Vision in Kluwer International Series in Engineering and Computer Science.Google Scholar
  44. 44.
    T. Lindeberg and J.O. Eklundh, On the computation of a scale-space primal sketch,J. Visual Commun. Image Represent. 2(1): 55–78, 1991.Google Scholar
  45. 45.
    T. Lindeberg, Scale-space behavior of local extrema and blobs,J. Math. Imag. Vis. 1:65–99, March 1992.Google Scholar
  46. 46.
    T. Lindeberg and J.O. Eklundh, The scale-space primal sketch: Construction and experiments,Image Vis. Comput. 10:3–18, 1992.Google Scholar
  47. 47.
    T. Lindeberg, Discrete derivative approximations with scale-space properties: A basis for low-level feature extraction,J. Math. Imag. Vis., 1993 (in press).Google Scholar
  48. 48.
    T. Lindeberg, Effective scale: A natural unit for measuring scale-space lifetime,IEEE Trans. Patt. Anal. Mach. Intell., 1993 (in press).Google Scholar
  49. 49.
    T. Lindeberg, On scale selection for differential operators,Proc. 8th Scandinavian Confer. Image Anal., Tromsö, Norway, pp. 857–866, May 1993.Google Scholar
  50. 50.
    T. Lindeberg and J. Gårding, Shape from texture from a multiscale perspective,Proc. 4th Intern. Conf. Comput. Vis., Berlin, pp. 683–691, May 1993.Google Scholar
  51. 51.
    D.G. Lowe,Perceptual Organization and Visual Recognition, Boston: Kluwer Academic Publishers, 1985.Google Scholar
  52. 52.
    J. Malik, Interpreting line drawings of curved objects,Intern. J. Comput. Vis. 1:73–104, 1987.Google Scholar
  53. 53.
    D. Marr, Early processing of visual information,Phil. Trans. Royal Soc. London (B), 273:483–524, 1976.Google Scholar
  54. 54.
    D. Marr,Vision, W.H. Freeman: New York, 1982.Google Scholar
  55. 55.
    J.C. Maxwell, On hills and dales,”The London, Edinburgh and Dublin Philosophical Magazine and J. of Science, 40(269): 421–425, 1870. Reprinted in W.D. Niven,The Scientific Papers of James Clark Maxwell, vol II, Dover Publications: New York, 1956.Google Scholar
  56. 56.
    F. Mokhtarian and A. Mackworth, Scale-based description and recognition of planar curves and two-dimensional objects,IEEE Trans. Patt. Anal. Mach. Intell. 8:34–43, 1986.Google Scholar
  57. 57.
    K. Pahlavan and J.O. Eklundh, A head-eye system—analysis and design,Comput. Vis. Graph. Image Process. 56(1):41–56, 1992.Google Scholar
  58. 58.
    A.P. Pentland, Extraction of deformable part models,Proc. 1st Europ. Conf. Comput. Vis., Antibes, France, pp. 397–401, 1990.Google Scholar
  59. 59.
    A.P. Pentland, Photometric motion,IEEE Trans. Patt. Anal. Mach. Intell., 13(9):879–890, 1991.Google Scholar
  60. 60.
    T. Poston and I. Steward,Catastrophe Theory and Its Applications, Pitman: London, 1978.Google Scholar
  61. 61.
    K. Rohr, Modelling and identification of characteristic intensity variations,Image Vis. Comput. 10(2):66–76, 1992.Google Scholar
  62. 62.
    E. Saund, Symbolic construction of a 2-D scale-space image,IEEE Trans. Patt. Anal. Mach. Intell. 12(8):817–831, 1990.Google Scholar
  63. 63.
    A.C. Sher and A. Rosenfeld, Detecting and extracting compact textured objects using pyramids, Tech. Rept. TR-1789, Computer Vision Laboratory, University of Maryland, Maryland, 1987.Google Scholar
  64. 64.
    F. Sjöberg and F. Bergholm, Extraction of diffuse edges by edge focusing,Patt. Recog. Letts. 7:181–190, 1988.Google Scholar
  65. 65.
    D. Terzopoulos, A. Witkin, and M. Kass, Constraints on deformable models: Recovering 3-D shape and nonrigid motion,Artificial Intelligence 36:91–123, 1988.Google Scholar
  66. 66.
    J.K. Tsotsos, Analyzing vision at the complexity level,Behav. Brain Sci. 13:423–469, 1990.Google Scholar
  67. 67.
    H. Voorhees and T. Poggio, Detecting textons and texture boundaries in natural images,Proc. 1st Int. Conf. Comput. Vis., London, 1987.Google Scholar
  68. 68.
    R. Watt,Visual Processing: Computational, Psychophysical and Cognitive Research, Lawrence Erlbaum Associates: London, 1988.Google Scholar
  69. 69.
    A.P. Witkin and J.M. Tenenbaum, On the role of structure in vision. InHuman and Machine Vision, J. Beck, B. Hope, and A. Rosenfeld, eds., Academic Press: New York, 1983.Google Scholar
  70. 70.
    A.P. Witkin, Scale-space filtering,Proc. 8th Intern. Joint Conf. Artif. Intell., Karlsruhe, West Germany, 1983, pp. 1019–1022.Google Scholar
  71. 71.
    A.L. Yuille and T.A. Poggio, Scaling theorems for zero-crossings,IEEE Trans. Patt. Anal. Mach. Intell., 8:15–25, 1986.Google Scholar
  72. 72.
    W. Zhang and F. Bergholm, An extension of Marr's signature based edge classification and other methods for determination of diffuseness and height of edges, as well as line width,Proc. 4th Intern. Conf. Comput. Vis., Berlin, pp. 183–191, May 1993.Google Scholar

Copyright information

© Kluwer Academic Publishers 1993

Authors and Affiliations

  • Tony Lindeberg
    • 1
  1. 1.Computational Vision and Active Perception Laboratory (CVAP), Department of Numerical Analysis and Computing ScienceRoyal Institute of TechnologyStockholmSweden

Personalised recommendations