ROBUSTNESS OF DIFFERENT FEATURES FOR ONE-CLASS CLASSIFICATION AND ANOMALY DETECTION IN WIRE ROPES

Esther-Sabrina Platzer, Joachim Denzler, Herbert Süße, Josef Nägele, Karl-Heinz Wehking

2009

Abstract

Automatic visual inspection of wire ropes is an important but challenging task. Anomalies in wire ropes usually are unobtrusive and their detection is a difficult job. Certainly, a reliable anomaly detection is essential to assure the safety of the ropes. A one-class classification approach for the automatic detection of anomalies in wire ropes is presented. Different well-established features from the field of textural defect detection are compared to context-sensitive features extracted by linear prediction. They are used to learn a Gaussian mixture model which represents the faultless rope structure. Outliers are regarded as anomaly. To evaluate the robustness of the method, a training set containing intentionally added, defective samples is used. The generalization ability of the learned model, which is important for practical life, is exploited by testing the model on different data sets from identically constructed ropes. All experiments were performed on real-life rope data. The results prove a high generalization ability, as well as a good robustness to outliers in the training set. The presented approach can exclude up to 90 percent of the rope as faultless without missing one single defect.

References

  1. Bailey, D. (1993). Frequency domain self-filtering for pattern detection. In Proceedings of the first New Zealand Conference on Image and Vision Computing, pages 237-243.
  2. Chen, C. H., Pau, L. F., and Wang, P. S. P., editors (1998). The Handbook of Pattern Recognition and Computer Vision (2nd Edition). World Scientific Publishing Co.
  3. EN 12927-7 (2004). Safety requirments for cableways installations designed to carry persons. ropes. inspection, repair and maintenance. European Norm: EN 12927-7:2004.
  4. Harlick, R. M., Shanmugam, K., and Dinstein, I. (1973). Textural Features for Image Classification. IEEE Transactions on Systems, Man and Cybernetics, 3(6):610-621.
  5. Hodge, V. J. and Austin, J. (2004). A Survey of Outlier Detection Methodologies. Artificial Intelligence Review, 22(2):85-126.
  6. Iivarinen, J. (2000). Surface Defect Detection with Histogram-Based Texture Features. volume 4197 of Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, pages 140-145.
  7. Kumar, A. and Pang, K. H. (2002). Defect Detection in Textured Materials Using Gabor Filters. IEEE Transactions on Industry Applications, 38(2):425-440.
  8. Mäenpää, T., Turtinen, M., and Pietikäinen, M. (2003). Real-time surface inspection by texture. Real-Time Imaging, 9(5):289-296.
  9. Makhoul, J. (1975). Linear Prediction: A Tutorial Review. Proceedings of the IEEE, 63(4):561- 580.
  10. Markou, M. and Singh, S. (2003). Novelty detection: a review - part 1: statistical approaches. Signal Processing, 83(12):2481 - 2497.
  11. Moll, D. (2003). Innovative procedure for visual rope inspection. Lift Report, 29(3):10-14.
  12. Ojala, T., Pietikäinen, M., and Harwood, D. (1996). A comparative study of texture measures with classification based on featured distributions. Pattern Recognition, 29(1):51-59.
  13. Ojala, T., Pietikäinen, M., and Mäenpää, T. (2000). Gray Scale and Rotation Invariant Texture Classification with Local Binary Patterns. In Proceedings of the European Conference on Computer Vision (ECCV), pages 404-420.
  14. Platzer, E.-S., Denzler, J., S üße, H., Nägele, J., and Wehking, K.-H. (2008). Challenging anomaly detection in wire ropes using linear prediction combined with oneclass classification. In Proceedings of the 13th International Fall Workshop Vision, Modeling and Visualization, pages 343-352.
  15. Rabiner, L. and Juang, B.-H. (1993). Fundementals of speech recognition. Prentice Hall PTR.
  16. Rautkorpi, R. and Iivarinen, J. (2005). Shape-Based Cooccurrence Matrices for Defect Classification. In Proceedings of the 14th Scandinaian Converence on Image Analysis (SCIA), pages 588-597.
  17. Tajeripour, F., Kabir, E., and Sheikhi, A. (2008). Fabric Defect Detection Using Modified Local Binary Patterns. EURASIP Journal on Advances in Signal Processing, 8(1):1-12.
  18. Tax, D. M. J. (2001). One-Class classification: Conceptlearning in the absence of counter-examples. Phd thesis, Delft University of Technology.
  19. Varma, M. and Zisserman, A. (2003). Texture Classification: Are Filter Banks Necessary? In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), volume 2, pages 691-698.
  20. Vartianinen, J., Sadovnikov, A., Kamarainen, J.-K., Lensu, L., and Kälviäinen, H. (2008). Detection of irregularities in regular patterns. Machine Vision and Applications, 19(4):249-259.
Download


Paper Citation


in Harvard Style

Platzer E., Denzler J., Süße H., Nägele J. and Wehking K. (2009). ROBUSTNESS OF DIFFERENT FEATURES FOR ONE-CLASS CLASSIFICATION AND ANOMALY DETECTION IN WIRE ROPES . 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 170-177. DOI: 10.5220/0001783801700177


in Bibtex Style

@conference{visapp09,
author={Esther-Sabrina Platzer and Joachim Denzler and Herbert Süße and Josef Nägele and Karl-Heinz Wehking},
title={ROBUSTNESS OF DIFFERENT FEATURES FOR ONE-CLASS CLASSIFICATION AND ANOMALY DETECTION IN WIRE ROPES},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={170-177},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001783801700177},
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 - ROBUSTNESS OF DIFFERENT FEATURES FOR ONE-CLASS CLASSIFICATION AND ANOMALY DETECTION IN WIRE ROPES
SN - 978-989-8111-69-2
AU - Platzer E.
AU - Denzler J.
AU - Süße H.
AU - Nägele J.
AU - Wehking K.
PY - 2009
SP - 170
EP - 177
DO - 10.5220/0001783801700177