Machine Vision and Applications

, Volume 21, Issue 5, pp 627–641 | Cite as

Impact of object extraction methods on classification performance in surface inspection systems

  • Stefan Raiser
  • Edwin Lughofer
  • Christian Eitzinger
  • James Edward Smith
Special Issue Paper

Abstract

In surface inspection applications, the main goal is to detect all areas which might contain defects or unacceptable imperfections, and to classify either every single ‘suspicious’ region or the investigated part as a whole. After an image is acquired by the machine vision hardware, all pixels that deviate from a pre-defined ‘ideal’ master image are set to a non-zero value, depending on the magnitude of deviation. This procedure leads to so-called “contrast images”, in which accumulations of bright pixels may appear, representing potentially defective areas. In this paper, various methods are presented for grouping these bright pixels together into meaningful objects, ranging from classical image processing techniques to machine-learning-based clustering approaches. One important issue here is to find reasonable groupings even for non-connected and widespread objects. In general, these objects correspond either to real faults or to pseudo-errors that do not affect the surface quality at all. The impact of different extraction methods on the accuracy of image classifiers will be studied. The classifiers are trained with feature vectors calculated for the extracted objects found in images labeled by the user and showing surfaces of production items. In our investigation artificially created contrast images will be considered as well as real ones recorded on-line at a CD imprint production and at an egg inspection system.

Keywords

Surface inspection Contrast images Object extraction Clustering Image classifiers 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Breiman L., Friedman J., Stone C.J., Olshen R.A.: Classification and Regression Trees. Chapman & Hall, Boca Raton (1993)Google Scholar
  2. 2.
    Caleb-Solly P., Smith J.E.: Adaptive surface inspection via interactive evolution. Image Vis. Comput. 25(7), 1058–1072 (2007)CrossRefGoogle Scholar
  3. 3.
    Daszykowski M., Walczak B., Massart D.L.: Looking for natural patterns in data. Part 1: Density based approach. Chemom. Intell. Lab. Syst. 56(2), 83–92 (2001)CrossRefGoogle Scholar
  4. 4.
    Ester, M., Kriegel, H.-P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Second International Conference on Knowledge Discovery and Data Mining, pp. 226–231. AAAI Press, Menlo Park (1996)Google Scholar
  5. 5.
    Gan, G., Ma, C., Wu, J.: Data Clustering: Theory, Algorithms and Applications. Society for Industrial and Applied Mathematics (SIAM), American Statistical Association, Philadelphia (2007)Google Scholar
  6. 6.
    Gonzalez R.C., Woods R.E.: Digital Image Processing, 2nd edn. Prentice-Hall, New Jersey (2002)Google Scholar
  7. 7.
    Halkidi M., Batistakis Y., Vazirgiannis M.: On clustering validation techniques. J. Intell. Inf. Syst. 17(2/3), 107–145 (2001)MATHCrossRefGoogle Scholar
  8. 8.
    Hastie T., Tibshirani R., Friedman J.: The Elements of Statistical Learning: Data Mining, Inference and Prediction. Springer, New York (2001)MATHGoogle Scholar
  9. 9.
    Hopkins B.: A new method for determining the type of distribution of plant individuals. Ann. Bot. 18, 213–226 (1954)Google Scholar
  10. 10.
    Iivarinen, J., Rauhamaa, J.: Surface inspection of web materials using the self-organizing map. In: Casasent, D.P. (ed.) Proceedings of the SPIE, vol. 3522, Intelligent Robots and Computer Vision XVII: Algorithms, Techniques, and Active Vision, pp. 96–103 (1998)Google Scholar
  11. 11.
    Jain A.K., Murty M.N., Flynn P.J.: Data clustering: a review. ACM Comput. Surv. 31(3), 264–323 (1999)CrossRefGoogle Scholar
  12. 12.
    Hashim, A.A., Campbell, J.G., Murtagh, F.: Flaw detection in woven textiles using space-dependent fourier transform. In: Owens, F.J. (ed.) ISSC ’97, Irish Signals and Systems Conference, pp. 241–252Google Scholar
  13. 13.
    Kim C.W., Koivo A.J.: Hierarchical classification of surface defects on dusty wood boards. Pattern Recognit. Lett. 15, 712–713 (1994)Google Scholar
  14. 14.
    Kubota T., Talekar P., Ma X., Sudarshan T.S.: A nondestructive automated defect detection system for silicon carbide wafers. Mach. Vis. Appl. 16, 170–176 (2005)CrossRefGoogle Scholar
  15. 15.
    Niskanen, M.: A visual training based approach to surface inspection. PhD thesis, Department of Electrical and Information Engineering, University of Oulu (2003)Google Scholar
  16. 16.
    Ozdemir, S., Baykut, A., Meylani, R., Ertüzün, A., Erçil, A.: Comparative evaluation of texture analysis algorithms for defect inspection of textile products. In: Proceedings of the International Conference on Pattern Recognition, pp. 1738–1741Google Scholar
  17. 17.
    Papari, G., Petkov, N.: Algorithm that mimics human perceptual grouping of dot patterns. In: Proceedings of the First International Symposium on Brain, Vision and Artificial Intelligence BVAI, Naples, October 2005, vol. 3704, pp. 497–506. Springer, Berlin (2005)Google Scholar
  18. 18.
    Pernkopf F.: 3D surface analysis using coupled hmms. Mach. Vis. Appl. 16(5), 298–305 (2005)CrossRefGoogle Scholar
  19. 19.
    Runkler, T.A.: Information Mining: Methoden, Algorithmen und Anwendungen intelligenter Datenanalyse. Vieweg, Gabler—Computational Intelligence, April 2000Google Scholar
  20. 20.
    Salvador, S., Chan, P.: Determining the number of clusters/segments in hierarchical clustering/segmentation algorithms. In: ICTAI 04 (2004)Google Scholar
  21. 21.
    Schael, M.: Texture fault detection using invariant textural features. In: Radig, B., Florczyk, S. (eds.) Proceedings of DAGM 2001, Pattern Recognition. Lecture Notes in Computer Science, vol. 2191, pp. 17–24. Springer, Berlin (2001)Google Scholar
  22. 22.
    Schölkopf B., Smola A.J.: Learning with Kernels—Support Vector Machines, Regularization, Optimization and Beyond. MIT Press, London (2002)Google Scholar
  23. 23.
    Shapiro L.G., Stockman G.C.: Computer Vision. Prentice-Hall, New Jersey (2001)Google Scholar
  24. 24.
    Shi J., Malik J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 888–905 (2000)CrossRefGoogle Scholar
  25. 25.
    Sibson R.: Slink: an optimally efficient algorithm for the single-link cluster method. Comput. J. 16(1), 30–34 (1973)CrossRefMathSciNetGoogle Scholar
  26. 26.
    Smith M.L.: Surface Inspection Techniques: Using the Integration of Innovative Machine Vision and Modelling Techniques. Professional Engineering Publishing, London (2000)Google Scholar
  27. 27.
    Stone M.: Cross-validatory choice and assessment of statistical predictions. Journal of the Royal Statistical Society 36, 111–147 (1974)MATHGoogle Scholar
  28. 28.
    Strehl A., Ghosh J.: Cluster ensembles—a knowledge reuse framework for combining multiple partitions. J. Mach. Learn. Res. 3, 583–617 (2002)CrossRefMathSciNetGoogle Scholar
  29. 29.
    Vapnik V.: Statistical Learning Theory. Wiley, New York (1998)MATHGoogle Scholar
  30. 30.
    Wagstaff, K., Cardie, C.: Clustering with instance-level constraints. In: Proceedings of the Seventeenth International Conference on Machine Learning, pp. 1103–1110 (2000)Google Scholar
  31. 31.
    Wang, W., Yang, J., Muntz, R.R.: STING: a statistical information grid approach to spatial data mining. In: Twenty-Third International Conference on Very Large Data Bases, Athens, Greece, pp. 186–195. Morgan Kaufmann, San Francisco (1997)Google Scholar
  32. 32.
    Wasserman P.D.: Advanced Methods in Neural Computing. Van Nostrand Reinhold, New York (1993)MATHGoogle Scholar
  33. 33.
    Wolpert D.H.: No free lunch theorems for optimization. IEEE Trans. Evol. Comput. 1(1), 67–82 (1997)CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag 2009

Authors and Affiliations

  • Stefan Raiser
    • 1
  • Edwin Lughofer
    • 1
  • Christian Eitzinger
    • 2
  • James Edward Smith
    • 3
  1. 1.Johannes Kepler University LinzLinzAustria
  2. 2.PROFACTOR GmbHSteyr-GleinkAustria
  3. 3.University of the West of EnglandBristolUK

Personalised recommendations