Advertisement

Imbalanced Learning Ensembles for Defect Detection in X-Ray Images

  • José Francisco Díez-Pastor
  • César García-Osorio
  • Víctor Barbero-García
  • Alan Blanco- Álamo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7906)

Abstract

This paper describes the process of detection of defects in metallic pieces through the analysis of X-ray images. The images used in this work are highly variable (several different pieces, different views, variability introduced by the inspection process such as positioning the piece). Because of this variability, the sliding window technique has been used, an approach based on data mining. Experiments have been carried out with various window sizes, several feature selection algorithms and different classification algorithms, with a special focus on learning unbalanced data sets. The results show that Bagging achieved significantly better results than decision trees by themselves or combined with SMOTE or Undersampling.

Keywords

Non Destructive testing ensemble learning X-ray Bagging Undersampling SMOTE 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cartz, L.: Nondestructive Testing: Radiography, Ultrasonics, Liquid Penetrant, Magnetic Particle, Eddy Current. Asm International (1995)Google Scholar
  2. 2.
    Spencer, F.: Visual inspection research project report on benchmark inspections. Technical report, Office of Aviation Research Washington, D.C. 20591: U.S. Department of Transportation, Federal Aviation Administration,Washington, DC (1996)Google Scholar
  3. 3.
    Liao, T.: Classification of welding flaw types with fuzzy expert systems. Expert Systems with Applications 25, 101–111 (2003)CrossRefGoogle Scholar
  4. 4.
    Rebuffel, V., Sood, S., Blakeley, B.: Defect detection method in digital radiography for porosity in magnesium casting. In: Materials Evaluation, ECNDT 2006 (2006)Google Scholar
  5. 5.
    Hanke, R., Hassler, U., Heil, K.: Fast automatic x-ray image processing by means of a new multistage filter for background modelling. In: Proceedings of the IEEE International Conference on Image Processing, ICIP 1994, vol. 1, pp. 392–396. IEEE (1994)Google Scholar
  6. 6.
    Ng, H.: Automatic thresholding for defect detection. Pattern Recognition Letters 27, 1644–1649 (2006)CrossRefGoogle Scholar
  7. 7.
    Saravanan, T., Bagavathiappan, S., Philip, J., Jayakumar, T., Raj, B.: Segmentation of defects from radiography images by the histogram concavity threshold method. Insight-Non-Destructive Testing and Condition Monitoring 49, 578–584 (2007)CrossRefGoogle Scholar
  8. 8.
    Anand, R., Kumar, P., et al.: Flaw detection in radiographic weld images using morphological approach. NDT & E International 39, 29–33 (2006)CrossRefGoogle Scholar
  9. 9.
    Wang, M., Chai, L.: Application of an improved watershed algorithm in welding image segmentation. Transactions China Welding Institution 28, 13 (2007)Google Scholar
  10. 10.
    Anand, R., Kumar, P., et al.: Flaw detection in radiographic weldment images using morphological watershed segmentation technique. NDT & E International 42, 2–8 (2009)CrossRefGoogle Scholar
  11. 11.
    Bay, H., Tuytelaars, T., Van Gool, L.: Surf: Speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  12. 12.
    García-Osorio, C., Díez-Pastor, J.F., Rodríguez, J.J., Maudes, J.: License plate number recognition - new heuristics and a comparative study of classifiers. In: Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics, Robotics and Automation, ICINCO 2008, vol. 1, pp. 268–273 (2008)Google Scholar
  13. 13.
    Jones, M., Rehg, J.: Statistical color models with application to skin detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, IEEE (1999)Google Scholar
  14. 14.
    Dlagnekov, L.: License plate detection using adaboost. Computer Science and Engineering Department, San Diego (2004)Google Scholar
  15. 15.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, vol. 1, pp. 511–518. IEEE (2001)Google Scholar
  16. 16.
    Wang, Y., Sun, Y., Lv, P., Wang, H.: Detection of line weld defects based on multiple thresholds and support vector machine. NDT & E International 41, 517–524 (2008)CrossRefGoogle Scholar
  17. 17.
    Mery, D.: Automated detection of welding discontinuities without segmentation. Materials Evaluation, 657–663 (2011)Google Scholar
  18. 18.
    Belaifa, S., Tridi, M., Nacereddine, N.: Weld defect classification using em algorithm for gaussian mixture model. In: SETIT Tunisia 2005 (2005)Google Scholar
  19. 19.
    Montabone, S., Soto, A.: Human detection using a mobile platform and novel features derived from a visual saliency mechanism. Image and Vision Computing 28, 391–402 (2010)CrossRefGoogle Scholar
  20. 20.
    Haralick, R., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Transactions on Systems, Man and Cybernetics, 610–621 (1973)Google Scholar
  21. 21.
    Hall, M.: Correlation-based feature selection for machine learning. PhD thesis, The University of Waikato (1999)Google Scholar
  22. 22.
    Yu, L., Liu, H.: Feature selection for high-dimensional data: A fast correlation-based filter solution. In: Machine Learning-International Workshop Then Conference, vol. 20, pp. 856–863 (2003)Google Scholar
  23. 23.
    Guyon, I., Weston, J., Barnhill, S., Vapnik, V.: Gene selection for cancer classification using support vector machines. Machine Learning 46, 389–422 (2002)MATHCrossRefGoogle Scholar
  24. 24.
    Chawla, N., Japkowicz, N., Kotcz, A.: Editorial: special issue on learning from imbalanced data sets. ACM SIGKDD Explorations Newsletter 6, 1–6 (2004)CrossRefGoogle Scholar
  25. 25.
    Fawcett, T.: An introduction to roc analysis. Pattern Recognition Letters 27, 861–874 (2006)CrossRefGoogle Scholar
  26. 26.
    Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research 16, 321–357 (2002)MATHGoogle Scholar
  27. 27.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: an update. SIGKDD Explor. Newsl. 11, 10–18 (2009)CrossRefGoogle Scholar
  28. 28.
    Quinlan, J.: C4.5: Programs for Machine Learning. Morgan Kauffman (1993)Google Scholar
  29. 29.
    Cieslak, D.A., Hoens, T.R., Chawla, N.V., Kegelmeyer, W.P.: Hellinger distance decision trees are robust and skew-insensitive. Data Min. Knowl. Discov. 24, 136–158 (2012)MathSciNetMATHCrossRefGoogle Scholar
  30. 30.
    Provost, F., Domingos, P.: Tree induction for probability-based ranking. Machine Learning 52, 199–215 (2003)MATHCrossRefGoogle Scholar
  31. 31.
    Breiman, L.: Bagging Predictors. Machine Learning 24, 123–140 (1996)MathSciNetMATHGoogle Scholar
  32. 32.
    Dietterich, T.: Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation 10, 1895–1923 (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • José Francisco Díez-Pastor
    • 1
  • César García-Osorio
    • 1
  • Víctor Barbero-García
    • 1
  • Alan Blanco- Álamo
    • 1
  1. 1.University of BurgosSpain

Personalised recommendations