Enhanced Image Segmentation Using Quality Threshold Clustering for Surface Defect Categorisation in High Precision Automotive Castings

  • Iker Pastor-López
  • Igor Santos
  • Jorge de-la-Peña-Sordo
  • Iván García-Ferreira
  • Asier G. Zabala
  • Pablo García Bringas
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 239)


Foundry is an important industry that supplies key products to other important sectors of the society. In order to assure the quality of the final product, the castings are subject to strict safety controls. One of the most important test in these controls is surface quality inspection. In particular, our work focuses on three of the most typical surface defects in iron foundries: inclusions, cold laps and misruns. In order to automatise this process, we introduce the QT Clustering approach to increase the perfomance of a segmentation method. Finally, we categorise resulting areas using machine-learning algorithms. We show that with this addition our segmentation method increases its coverage.


Computer Vision Machine-Learning Defect Categorisation Foundry 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Mital, A., Govindaraju, M., Subramani, B.: A comparison between manual and hybrid methods in parts inspection. Integrated Manufacturing Systems 9(6), 344–349 (1998)CrossRefGoogle Scholar
  2. 2.
    Watts, K.P.: The effect of visual search strategy and overlays on visual inspection of castings. Master’s thesis, Iowa State University (2011)Google Scholar
  3. 3.
    Pernkopf, F., O’Leary, P.: Image acquisition techniques for automatic visual inspection of metallic surfaces. NDT & E International 36(8), 609–617 (2003)CrossRefGoogle Scholar
  4. 4.
    vom Stein, D.: Automatic visual 3-d inspection of castings. Foundry Trade Journal 180(3641), 24–27 (2007)Google Scholar
  5. 5.
    Castleman, K.: 2nd edn. Prentice-Hall, Englewood Clliffs, New Jersey (1996)Google Scholar
  6. 6.
    Pastor-Lopez, I., Santos, I., Santamaria-Ibirika, A., Salazar, M., de-la Pena-Sordo, J., Bringas, P.: Machine-learning-based surface defect detection and categorisation in high-precision foundry. In: 2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA), pp. 1359–1364 (2012)Google Scholar
  7. 7.
    Heyer, L.J., Kruglyak, S., Yooseph, S.: Exploring expression data: identification and analysis of coexpressed genes. Genome Research 9(11), 1106–1115 (1999)CrossRefGoogle Scholar
  8. 8.
    Ugarte-Pedrero, X., Santos, I., Bringas, P., Gastesi, M., Esparza, J.: Semi-supervised learning for packed executable detection. In: Proceedings of the 5th International Conference on Network and System Security (NSS), pp. 342–346 (2011)Google Scholar
  9. 9.
    Gonzalez, R., Woods, R.: Digital image processing, vol. 16(716). Addison-Wesley, Reading (1992)Google Scholar
  10. 10.
    Viola, P., Jones, M.: Robust real-time face detection. International Journal of Computer Vision 57(2), 137–154 (2004)CrossRefGoogle Scholar
  11. 11.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press (1995)Google Scholar
  12. 12.
    Chawla, N., Bowyer, K., Hall, L., Kegelmeyer, W.: SMOTE: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research 16(3), 321–357 (2002)MATHGoogle Scholar
  13. 13.
    Cooper, G.F., Herskovits, E.: A bayesian method for constructing bayesian belief networks from databases. In: Proceedings of the 1991 Conference on Uncertainty in Artificial Intelligence (1991)Google Scholar
  14. 14.
    Geiger, D., Goldszmidt, M., Provan, G., Langley, P., Smyth, P.: Bayesian network classifiers. Machine Learning, 131–163 (1997)Google Scholar
  15. 15.
    Amari, S., Wu, S.: Improving support vector machine classifiers by modifying kernel functions. Neural Networks 12(6), 783–789 (1999)CrossRefGoogle Scholar
  16. 16.
    Maji, S., Berg, A., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: Proc. CVPR, vol. 1, p. 4 (2008)Google Scholar
  17. 17.
    Üstün, B., Melssen, W., Buydens, L.: Visualisation and interpretation of support vector regression models. Analytica Chimica Acta 595(1-2), 299–309 (2007)CrossRefGoogle Scholar
  18. 18.
    Cho, B., Yu, H., Lee, J., Chee, Y., Kim, I., Kim, S.: Nonlinear support vector machine visualization for risk factor analysis using nomograms and localized radial basis function kernels. IEEE Transactions on Information Technology in Biomedicine 12(2), 247 (2008)CrossRefGoogle Scholar
  19. 19.
    Garner, S.: Weka: The Waikato environment for knowledge analysis. In: Proceedings of the 1995 New Zealand Computer Science Research Students Conference, pp. 57–64 (1995)Google Scholar
  20. 20.
    Quinlan, J.: C4. 5 programs for machine learning. Morgan Kaufmann Publishers (1993)Google Scholar
  21. 21.
    Breiman, L.: Random forests. Machine learning 45(1), 5–32 (2001)MATHCrossRefGoogle Scholar
  22. 22.
    Singh, Y., Kaur, A., Malhotra, R.: Comparative analysis of regression and machine learning methods for predicting fault proneness models. International Journal of Computer Applications in Technology 35(2), 183–193 (2009)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Iker Pastor-López
    • 1
  • Igor Santos
    • 1
  • Jorge de-la-Peña-Sordo
    • 1
  • Iván García-Ferreira
    • 1
  • Asier G. Zabala
    • 1
  • Pablo García Bringas
    • 1
  1. 1.S3Lab, DeustoTech - ComputingUniversity of DeustoBilbaoSpain

Personalised recommendations