WELDING INSPECTION USING NOVEL SPECULARITY FEATURES AND A ONE-CLASS SVM

Fabian Timm, Sascha Klement, Erhardt Barth, Thomas Martinetz

2009

Abstract

We present a framework for automatic inspection of welding seams based on specular reflections. Therefore, we introduce a novel feature set -- called specularity features (SPECs) -- describing statistical properties of specular reflections. For classification we use a one-class support-vector approach. The SPECs significantly outperform statistical geometric features and raw pixel intensities, since they capture more complex characteristics and depencies of shape and geometry.We obtain an error rate of 9%, which corresponds to the level of human performance.

References

  1. Boser, B., Guyon, I., and Vapnik, V. (1992). A training algorithm for optimal margin classifiers. In Haussler, D., editor, Proc. of the 5th Annual ACM Workshop on Computational Learning Theory, pages 144-152. ACM Press.
  2. Chen, Y. Q., Nixon, M. S., and Thomas, D. W. (1995). Statistical geometrical features for texture classification. Pattern Recognition, 28(4):537-552.
  3. Chiu, S. and Perng, M. (2007). Reflection-area-based feature descriptor for solder joint inspection. Machine Vision and Applications, 18(2):95-106.
  4. Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3):273-297.
  5. Driels, M. and Lee, C. (1988). Feature selection for automatic visual inspection of solder joints. The Int. Journal of Advanced Manufacturing Technology, 3:3-32.
  6. Fukunaga, K. (1972). Introduction to Statistical Pattern Recognition. Academic Press.
  7. Kim, J. and Cho, H. (1995). Neural network-based inspection of solder joints using a circular illumination. Image and Vision Computing, 13(6):479-490.
  8. Ko, K. and Cho, H. (2000). Solder joints inspection using a neural network and fuzzy rule-based classification method. IEEE Transactions on Electronics Packaging Manufacturing, 23(2):93-103.
  9. Labusch, K., Timm, F., and Martinetz, T. (2008). Simple incremental one-class support vector classification. In Rigoll, G., editor, Proc. of the 30th German Pattern Recognition Symposium DAGM, volume 5096 of Lecture Notes in Computer Science, pages 21-30. Springer.
  10. Ong, T., Samad, Z., and Ratnam, M. (2008). Solder joint inspection with multi-angle imaging and an artificial neural network. The Int. Journal of Advanced Manufacturing Technology, 38(5-6):455-462.
  11. Poechmueller, W., Glesner, M., Listl, L., and Mengel, P. (1991). Automatic classification of solder joint images. In Proc. of the Int. Joint Conf. on Neural Networks, volume 2, pages 933-940. IEEE Computer Society Press.
  12. Russ, J. C. (2007). The Image Processing Handbook. CRC Press.
  13. Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., and Williamson, R. C. (2001). Estimating the support of a high-dimensional distribution. Neural Computation, 13(7):1443-1471.
  14. Stone, M. (1974). Cross-validatory choice and assessment of statistical predictions. Journal of the Royal Statistics Society, 36:111-147.
  15. Tax, D. M. J. and Duin, R. P. W. (2004). Support vector data description. Machine Learning, 54(1):45-66.
  16. Timm, F., Klement, S., and Martinetz, T. (2008). Fast model selection for maxminover-based training of support vector machines. In Proc. of the 19th Int. Conf. on Pattern Recognition, Florida, USA. IEEE Computer Society Press. to appear.
  17. Vapnik, V. (1995). The Nature of Statistical Learning Theory. Springer Verlag, New York.
  18. Walker, R. and Jackway, P. T. (1996). Statistical geometric features: Extensions for cytological texture analysis. In Proc. of the 13th Int. Conf. on Pattern Recognition, pages 790-794. IEEE Computer Society Press.
Download


Paper Citation


in Harvard Style

Timm F., Klement S., Barth E. and Martinetz T. (2009). WELDING INSPECTION USING NOVEL SPECULARITY FEATURES AND A ONE-CLASS SVM . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 145-152. DOI: 10.5220/0001776301450152


in Bibtex Style

@conference{visapp09,
author={Fabian Timm and Sascha Klement and Erhardt Barth and Thomas Martinetz},
title={WELDING INSPECTION USING NOVEL SPECULARITY FEATURES AND A ONE-CLASS SVM},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={145-152},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001776301450152},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)
TI - WELDING INSPECTION USING NOVEL SPECULARITY FEATURES AND A ONE-CLASS SVM
SN - 978-989-8111-69-2
AU - Timm F.
AU - Klement S.
AU - Barth E.
AU - Martinetz T.
PY - 2009
SP - 145
EP - 152
DO - 10.5220/0001776301450152