Advertisement

Contour Detection for Industrial Image Processing by Means of Level Set Methods

  • J. Marot
  • Y. Caulier
  • A. Kuleschov
  • K. Spinnler
  • S. Bourennane
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5259)

Abstract

We consider the problem of the automatic inspection of industrial metal pieces. The purpose of the work presented in this paper is to derive a method for defect detection. For the first time in this context we adapt level set method to distinguish hollow regions in the metal pieces from the grinded surface. We compare this method with Canny edge enhancement and with a thresholding method based on histogram computation. The experiments performed on two industrial images show that the proposed method retrieves correctly fuzzy contours and is robust against noise.

Keywords

Defect Detection Outer Contour Contour Detection Edge Detection Method Gradient Vector Flow 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Pal, N., Pal, S.: A review on image segmentation techniques. Pattern Recognition 26(9), 1277–1294 (1993)CrossRefGoogle Scholar
  2. 2.
    Ayache, N., Faugeras, O.D.: HYPER: a new approach for the recognition and positionning of two-dimensionnal objects. IEEE-PAMI 8(1), 44–54 (1986)CrossRefGoogle Scholar
  3. 3.
    Karoui, I., Fablet, R., Boucher, J.-M., Augustin, J.-M.: Region-based segmentation using texture statistics and level-set methods. IEEE ICASSP 2(12), 693–696 (2006)Google Scholar
  4. 4.
    Kiryati, N., Bruckstein, A.M.: What’s in a set of points? [straight line fitting]. IEEE Trans. on Pattern Analysis and Machine Intelligence 14(4), 496–500 (1992)CrossRefGoogle Scholar
  5. 5.
    Aghajan, H.K., Kailath, T.: Sensor array processing techniques for super resolution multi-line-fitting and straight edge detection. IEEE IP 2(4), 454–465 (1993)Google Scholar
  6. 6.
    Marot, J., Bourennane, S.: Subspace-Based and DIRECT Algorithms for Distorted Circular Contour Estimation. IEEE-IP 16(9), 2369–2378 (2007)MathSciNetzbMATHGoogle Scholar
  7. 7.
    Canny, J.: A computational approch to edge detection. IEEE Trans. Pattern Anal. Machine Intell. 8, 679–714 (1986)CrossRefGoogle Scholar
  8. 8.
    Otsu, N.: A threshold selection method from gray level histogram. IEEE Trans. Syst. Man Cybern. 9, 62–66 (1979)CrossRefGoogle Scholar
  9. 9.
    Kuleschow, A., Spinnler, K.: New Methods for Segmentation of Images Considering the Human Vision Principles. In: Computer Vision and Graphics ICCVG, Warsaw Proc, pp. 1037–1042 (2004)Google Scholar
  10. 10.
    Chi-Ho, C., Pang, G.K.H.: Fabric defect detection by Fourier analysis. IEEE Transactions on Industry Applications 36(5), 1267–1276 (2000)CrossRefGoogle Scholar
  11. 11.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active Contour Model. Int. J. Computer Vision, 321–331 (1988)Google Scholar
  12. 12.
    Xu, C., Prince, J.L.: Gradient vector flow: a new external force for snakes. In: IEEE Comp. Soc. Conf. Comp. Vis., Pat. Rec., pp. 66–71 (1997)Google Scholar
  13. 13.
    Xianghua, X., Mirmehdi, M.: RAGS: region-aided geometric snake. IEEE Trans. on IP 13(5), 640–652 (2004)MathSciNetGoogle Scholar
  14. 14.
    Aujol, J.F., Aubert, G., Blanc-Féraud, L.: Wavelet-based level set evolution for classification of textured images. IEEE Trans. on Image Processing 12(12), 1634–1641 (2003)MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Mitchell, I.M.: The Flexible, Extensible and Efficient Toolbox of Level Set Methods. Journal of Scientific Computing (December 2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • J. Marot
    • 1
  • Y. Caulier
    • 1
  • A. Kuleschov
    • 1
  • K. Spinnler
    • 1
  • S. Bourennane
    • 2
  1. 1.Fraunhofer Institut IISErlangenGermany
  2. 2.Univ. Paul Cézanne, Ecole Centrale Marseille, Institut Fresnel (CNRS UMR 6133)Marseille cedex 20France

Personalised recommendations