Skip to main content
SpringerLink
Log in

Detection of surface defects on raw steel blocks using Bayesian network classifiers

  • Theoretical Advances
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

This paper proposes an approach that detects surface defects with three-dimensional characteristics on scale-covered steel blocks. The surface reflection properties of the flawless surface changes strongly. Light sectioning is used to acquire the surface range data of the steel block. These sections are arbitrarily located within a range of a few millimeters due to vibrations of the steel block on the conveyor. After the recovery of the depth map, segments of the surface are classified according to a set of extracted features by means of Bayesian network classifiers. For establishing the structure of the Bayesian network, a floating search algorithm is applied, which achieves a good tradeoff between classification performance and computational efficiency for structure learning. This search algorithm enables conditional exclusions of previously added attributes and/or arcs from the network. The experiments show that the selective unrestricted Bayesian network classifier outperforms the naïve Bayes and the tree-augmented naïve Bayes decision rules concerning the classification rate. More than 98% of the surface segments have been classified correctly.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1a–d
Fig. 2
Fig. 3
Fig. 4a–c
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Newman TS, Jain AK (1995) A survey of automated visual inspection. Computer Vis Image Und 61(2):231–262

    Article  Google Scholar 

  2. Pernkopf F, O’Leary P (2003) Image acquisition techniques for automatic visual inspection of metallic surfaces. NDT&E Int 36(8):609–617

    Google Scholar 

  3. Dupont F, Odet C, Carton M (1997) Optimization of the recognition of defects in flat steel products with the cost matrices theory. NDT&E Int 30(1):3–10

    Google Scholar 

  4. Pernkopf F, O’Leary P (2002) Visual inspection of machined metallic high-precision surfaces. Eurasip J Appl Signal Process 2002(7):667–678

    Article  Google Scholar 

  5. Torrance KE, Sparrow EM (1967) Theory for off-specular reflection from roughened surfaces. J Opt Soc Am 57(9):1105–1114

    Google Scholar 

  6. Nayar SK, Ikeuchi K, Kanade T (1991) Surface reflection: physical and geometrical perspectives. IEEE Trans Pattern Anal Machine Intell 13(7):611–634

    Article  Google Scholar 

  7. Platero C, Fernandez C, Campoy P, Aracil R (1996) Surface analysis of cast aluminum by means of artificial vision and A.I. based techniques. Mach Vis Appl 2665:36–46

    Google Scholar 

  8. Machine vision applications in industrial inspection (various papers). Proceedings of SPIE. Homepage at http://www.spie.org/

  9. Indyk D, Velastin SA (1994) Survey of range vision systems. Mechatronics 4(4):417–449

    Article  Google Scholar 

  10. Curless B, Levoy M (1995) Better optical triangulation through spacetime analysis. In: Proceedings of the 5th international conference on computer vision (ICCV’95), Boston, Massachusetts, June 1996, pp 987–994

  11. Kanade T (1987) Three-dimensional machine vision. Kluwer, Dordrecht, The Netherlands

    Google Scholar 

  12. Johannesson M (1995) SIMD architectures for range and radar imaging. PhD thesis, Department of Electrical Engineering, Linköping University, Sweden

  13. SICK IVP (Integrated Vision Products). IVP Ranger SAH5 product information. Company homepage at http://www.ivp.se.

  14. Long AE, Long CA (2001) Surface approximation and interpolation via matrix SVD. Coll Math J 32(1):20–25

    MathSciNet  Google Scholar 

  15. Golub GH, Van Loan CF (1996) Matrix computations, 3rd edn. John Hopkins University Press, Baltimore

    Google Scholar 

  16. Pernkopf F, Pernkopf F, O’Leary P (2002) Detection of surface defects on raw milled steel blocks using range imaging. In: Proceedings of the 14th IT&S/SPIE annual symposium on electronic imaging, San Jose, California, January 2002, pp 170–181

  17. Datta BN (1995) Numerical linear algebra and applications. Brooks/Cole Publishing, Belmont, California

    Google Scholar 

  18. Pernkopf F (2002) Automatic visual inspection of metallic surfaces. PhD thesis, University of Leoben, Austria

  19. Sonka M, Hlavac V, Boyle R (1999) Image processing, analysis, and machine vision, 2nd edn. International Thomson Publishing, London

    Google Scholar 

  20. Gonzalez RC, Woods RE (1992) Digital image processing, 3rd edn. Addison-Wesley, Reading, Massachusetts

    Google Scholar 

  21. Pernkopf F, O’Leary P (2003) Shape description and analysis of range data for milled steel blocks. In: Proceedings of the 15th IT&S/SPIE symposium on electronic imaging, Santa Clara, California, January 2003, pp 74–81

  22. Jain AK, Zongker D (1997) Feature selection: evaluation, application, and small sample performance. IEEE Trans Pattern Anal Machine Intell 19(2):153–158

    Article  Google Scholar 

  23. Dash M, Liu H (1997) Feature selection for classification. Intell Data Anal 1(3):131–156

    Article  MATH  Google Scholar 

  24. Kohavi R, John GH (1997) Wrappers for feature subset selection. Artif Intell 97(1–2):273–324

    Article  Google Scholar 

  25. Jain AK, Chandrasekaran B (1982) Dimensionality and sample size considerations in pattern recognition in practice, vol 2. In: Handbook of Statistics. North-Holland, Amsterdam

  26. Pearl J (1988) Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann, San Francisco, California

    Google Scholar 

  27. Friedman N, Geiger D, Goldszmidt M (1997) Bayesian network classifiers. Machine Learn 29:131–163

    Article  Google Scholar 

  28. Singh M, Provan GM (1996) Efficient learning of selective Bayesian network classifiers. In: Proceedings of the 13th international conference on machine learning (ICML’96), Bari, Italy, July 1996, pp 453–461

  29. Jensen FV (1996) An introduction to Bayesian networks. UCL Press, London

    Google Scholar 

  30. Cowell RG, Dawid AP, Lauritzen SL, Spiegelhalter DJ (1999) Probabilistic networks and expert systems, 1st edn. Springer, Berlin Heidelberg New York

    Google Scholar 

  31. Heckerman D (1995) A tutorial on learning Bayesian networks. Technical report MSR-TR-95-06, Microsoft Research, Redmond, Washington

  32. Duda RO, Hart PE, Stork DG (2000) Pattern classification, 2nd edn. Wiley, New York

    Google Scholar 

  33. Pudil P, Novovičová J, Kittler J (1994) Floating search methods in feature selection. Pattern Recogn Lett 15(11):1119–1125

    Article  Google Scholar 

  34. Pernkopf F, O’Leary P (2003) Floating search algorithm for structure learning of Bayesian network classifiers. Pattern Recogn Lett 24(15):2839–2848

    Article  Google Scholar 

  35. Kittler J (1978) Feature set search algorithms. In: Chen CH (ed) Pattern recognition and signal processing. Sijtho and Noordho, Alphen aan den Rijn, The Netherlands, pp 41–60

    Google Scholar 

  36. Keogh EJ, Pazzani MJ (1999) Learning augmented Bayesian classifiers: a comparison of distribution-based and classification-based approaches. In: Proceedings of the 7th international workshop on artificial intelligence and statistics (Uncertainty’99), Fort Lauderdale, Florida, January 1999, pp 225–230

  37. Fayyad UM, Irani KB (1993) Multi-interval discretization of continuous-valued attributes for classification learning. In: Proceedings of the 13th international joint conference on artificial intelligence, Chambéry, France, August/September 1993, pp 1022–1027

Download references

Acknowledgements

The author is grateful to Prof. Gernot Kubin for his valuable comments on this paper, and to Ingo Reindl and Voest Alpine Donawitz Stahl for providing the data. Parts of the work were done while the author was with the Institute of Automation at the University of Leoben, Austria.

Author information

Author notes

  1. Franz Pernkopf

    Present address: Institute of Signal Processing and Speech Communication, Graz University of Technology, Inffeldgasse 12, 8010, Graz, Austria

Authors and Affiliations

  1. Department of Electrical Engineering, University of Washington, M254 EE/CSE Building, Box 352500, WA, Seattle, 98195-2500, USA

    Franz Pernkopf

Authors
  1. Franz Pernkopf
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Franz Pernkopf.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Pernkopf, F. Detection of surface defects on raw steel blocks using Bayesian network classifiers. Pattern Anal Applic 7, 333–342 (2004). https://doi.org/10.1007/s10044-004-0232-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-004-0232-3

Keywords

Search

Navigation