Machine Vision and Applications

, Volume 8, Issue 1, pp 63–75 | Cite as

Texture crack detection

  • Keng Yew Song
  • Maria Petrou
  • Josef Kittler


Automatic visual inspection has become one of the active research issues in machine vision technology in the past decades. Most of the methodologies developed address the problems of defect detection on a nontextured or regularly textured surface. However, problems in detecting defects on a randomly textured surface, especially cracks, have not received much attention. In this paper, we present a novel algorithm that uses a Wigner model to identify cracks in complex textural backgrounds, regardless of whether the inspected surface is randomly or regularly textured. We also investigate the windowing characteristics of the Wigner distribution and their impact on crack detection. Some of the Brodatz' natural texture images have been used for evaluating the performance of the algorithm. Promising results are obtained and presented in this paper.

Key words

Texture analysis Crack detection Wigner distribution Surface inspection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bastiaans MJ (1978) The Wigner distribution function applied to optical signals and systems. Opt Commun 25:26–30Google Scholar
  2. 2.
    Bastiaans MJ (1979) Wigner distribution function and its application to first order optics. J Opt Soc Am 69:ccc-cccGoogle Scholar
  3. 3.
    Campbell FW, Robson JG (1968) Application of Fourier analysis to the visibility of gratings. J Physiol 197:551–566Google Scholar
  4. 4.
    Claasen TACM, Mecklenbrauker WFG (1980) The Wigner distribution - a tool for time-frequency signal analysis; part 3: relations with other time frequency signal transformation. Philips J Res 35:372–398Google Scholar
  5. 5.
    D'astous A, Jernigan ME (1984) Texture discritmination based on detailed measures of the power spectrum. Proceedings of the 7th International Conference on Pattern Recognition 6:269–285Google Scholar
  6. 6.
    Daugman GF (1985) Uncertainty relatin for resolution in space, spatial frequency, and orientation optimized by two dimensional visual cortical filters. J Opt Soc Am 2:1160–1169Google Scholar
  7. 7.
    Flandrin P (1984) Some features of time frequency representation of multicomponent signals. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp41B.41–41B.44Google Scholar
  8. 8.
    Hancock E, Kittler J (1990) Edge-labelling using dictionary relaxation. IEEE Patt Anal Machin Intell 12:165–181Google Scholar
  9. 9.
    Hubel DG, Wiesel TN (1962) Receptive fields, binocular interaction, and functional architecture in the cat's visual cortex. J Physiol London 160:106–154Google Scholar
  10. 10.
    Hubel DG, Wiesel TN (1974) Sequence regularity and geometry of orientation columns in the monkey striate cortex. J Comp Neurol 158:267–293Google Scholar
  11. 11.
    Jacobson L, Wechsler H (1982) The Wigner distribution and its usefulness for 2D image processing. Proceedings of the 6th International Joint Conference on Pattern Recognition, pp 19–22Google Scholar
  12. 12.
    Jacobson LD, Wechsler H (1988) Joint spatial/spatial-frequency representation. Signal Processing 14:37–68Google Scholar
  13. 13.
    Kaiser JF (1966) Digital filters. Wiley, New YorkGoogle Scholar
  14. 14.
    Maffei L, Fiorentini A (1973) The visual cortex as a spatial frequency analyzer. Vision Res 13:1255–1267Google Scholar
  15. 15.
    Martin W, Flandrin P (1984) Analysis of non-stationary process: short time periodograms versus a pseudo Wigner estimator. Schussler EURASI North Holland, Amsterdam, pp 455–459Google Scholar
  16. 16.
    Neisser U (1967) Cognitive psychology. Prentice Hall, Englewood cliffs, NJGoogle Scholar
  17. 17.
    Petrou M (1993) Optimal convolution filters and an algorithm for the detection of linear features. IEE Proceedings Communications, Speech and Vision pp 331–339Google Scholar
  18. 18.
    Pollen DA, Lee JR, Tayor JH (1971) How does the striate cortex begin the reconstruction of the visual world. Science 173:74–77Google Scholar
  19. 19.
    Qian S, Morris JM (1992) Wigner distribution decomposition and cross-term deleted representation. Signal Processing 27:125–144Google Scholar
  20. 20.
    Reed TJ, Wechsler H (1990) Segmentation of textured images and gestalt organisation using spatial/spatial-frequency representations. IEEE Trans Patt Anal Machine Intell 12:1–11Google Scholar
  21. 21.
    Rosenfeld A, Hummel R, Zucker S (1976) Scene labelling by relaxation operations. IEEE Trans Syst Man Cybernetics 6:269–285Google Scholar
  22. 22.
    Slepian D (1965) Analytic solution of two apodizatin problems. J Opt Soc Am 55:1110–1115Google Scholar
  23. 23.
    Wechsler H (1990) Computational vision. Academic Press, New YorkGoogle Scholar
  24. 24.
    Weszka JS, Dyer CR, Rosenfeld A (1976) A comparative study of texture measures for terrain classification. IEEE Trans Syst Man Cybernetics 6:269–285Google Scholar
  25. 25.
    Zucker SW, Krishoamuthy EV, Harr RL (1978) Relaxation process for relaxation labelling convergence speed and stability. IEEE Trans Syst Man Cybernetics 8:41–48Google Scholar

Copyright information

© Springer-Verlag 1995

Authors and Affiliations

  1. 1.University of Surrey Vision, Speech and Signal-Processing Research Group, Department of Electronic and Electrical EngineeringGuildfordUK

Personalised recommendations