Skip to main content
SpringerLink
Log in

Classification of defects in steel strip surface based on multiclass support vector machine

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In this paper, we use support vector machine to classify the defects in steel strip surface images. After image binarization, three types of image features, including geometric feature, grayscale feature and shape feature, are extracted by combining the defect target image and its corresponding binary image. For the classification model based on support vector machine, we utilize Gauss radial basis as the kernel function, determine model parameters by cross-validation and employ one-versus-one method for multiclass classifier. Experiment results show that support vector machine model outperforms the traditional classification model based on back-propagation neural network in average classification accuracy.

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. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Notes

  1. http://www.opencv.org.cn/

  2. http://www.csie.ntu.edu.tw/~cjlin/libsvm/

References

  1. Cecilio A, Xavier P, Andreu C (2003) K-SVCR: a multi-class support vector machine. J Neurocomputing 55(1–2):57–77. doi:10.1016/S0925-2312(03)00435-1

    Google Scholar 

  2. Chih-Wei H, Chih-Jen L (2002) A comparison of methods for multiclass support vector machines. IEEE Trans Neural Network 13(2):415–425. doi:10.1109/72.991427

    Article  Google Scholar 

  3. Choi C-H, Choi J-K, Kim Y-K et al (1996) Feature extraction algorithm based on adaptive wavelet packet for surface defect classification. Proc Int Conf Image Process, pages: 673–676. doi: 10.1109/ICIP.1996.560968

  4. Cortes C, Vapnik V (1995) Support-vector network. J Mach Learn 20(3):273–297

    MATH  Google Scholar 

  5. Heermann PD, Khazenie N (1992) Classification of multispectral remote sensing data using a back-propagation neural network. IEEE Trans Geosci Remote Sens 30(1):81–88. doi:10.1109/36.124218

    Article  Google Scholar 

  6. Hsu C-W, Chang C-C, Lin C-J (2003) A practical guide to support vector classification (Technical report). Department of Computer Science and Information Engineering, National Taiwan University. http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf

  7. Hsu K-Y, Lin S-H, Hsieh T-C (1995) A hybrid neural network for image classification. Opt Lasers Eng 123(2–3):167–183. doi:10.1016/0143-8166(95)00013-E

    Article  Google Scholar 

  8. Hu MK (1962) Visual pattern recognition by moment in variants. IEEE Trans Inform Theor 8:179–187

    MATH  Google Scholar 

  9. Khotanzad A, Lu J-H (1990) Classification of invariant image representations using a neural network. IEEE Trans Acoust Speech Signal Process 38(6):1028–1038. doi:10.1109/29.56063

    Article  Google Scholar 

  10. Kim C-K, Choi S-H, Joo W-J (2006) Classification of surface defect on steel strip by KNN classifier. J Korean Soc Precis Eng 23(8):80–88

    Google Scholar 

  11. Kwak C, Ventura A, Karim T (2000) A neural network approach for defect identification and classification on leather fabric. J Intell Manuf 11(5):485–499. doi:10.1023/A:1008974314490

    Article  Google Scholar 

  12. Lai K, Zhang H, Dai D (2003) New approach to classification of surface defects in steel plate based on fuzzy neural networks. Proc SPIE Int Soc Opt Eng 4929:447–456

    Google Scholar 

  13. Li L, Yu L, Zhang M et al (2006) Detection and classification of wood defects by ANN, IEEE International Conference on Mechatronics and Automation, 2235–224. doi:10.1109/ICMA.2006.257659

  14. Liu S, Liu J and Zhang L (2008) Classification of fabric defect based on PSO-BP neural network. Proceedings of Second International Conference on Genetic and Evolutionary Computing, pages: 137–140. doi:10.1109/WGEC.2008.47

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

    Article  MathSciNet  Google Scholar 

  16. Rumelhart E, Hinton E, Williams J (1986) Learning representations by back-propagating errors. Nature 323(6088):533–536

    Article  Google Scholar 

  17. Salavi R, Sohani M (2011) Image texture classification using Artificial Neural Network. Advances in Computing, Communication and Control, Part 1: Communications in Computer and Information Science 125:62–69. doi:10.1007/978-3-642-18440-6_8

    Article  Google Scholar 

  18. Song S-J, Kim H-J, Choi S-H et al (1997) Classification of surface defects on cold rolled strips by probabilistic neural networks. J Korean Soc Nondestr Test 17(3):162–173

    Google Scholar 

  19. Suralkar SR et al (2012) Texture image classification using support vector machine. Int J Comput Appl Tech 3(1):71–75

    Google Scholar 

  20. Trieber F (1989) On-line automatic defect detection and surface roughness measurement of steel strip. J Iron Steel Eng 66(9):26–33

    Google Scholar 

  21. Vapnik V (1995) The nature of statistical learning theory. Springer, New York, Berlin Heidelberg

    Book  MATH  Google Scholar 

  22. Vascotto M (1996) High speed surface defect identification on steel strip. Metall Plant Technol Int 4:70–73

    Google Scholar 

  23. Wong W-K et al (2009) Stitching defect detection and classification using wavelet transform and BP neural network

  24. Yang B et al (2011) Remote sensing image classification based on improved BP neural network. In proceedings of the 2011 International Symposium on Image and Data Fusion, pages: 1–4. doi: 10.1109/ISIDF.2011.6024276

  25. Zhang, W, Tang X and Yoshida T (2007) Text classification with support vector machine and back propagation neural network. Proceeding of the 7th international conference on computational science, 150–157

Download references

Acknowledgements

The work in this paper was supported partially by the National Natural Science Foundation of China (No. 61070009, 61100133) and Hubei Provincial Natural Science Funds for Distinguished Young Scholar of China (2010CDA090).

Author information

Authors and Affiliations

  1. State Key Lab of Software Engineering Computer School, Wuhan University, Wuhan, 430072, Hubei, China

    Huijun Hu & Yuanxiang Li

  2. College of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, 430065, Hubei, China

    Huijun Hu & Maofu Liu

  3. Zhejiang Dahua Tecnology Co. Ltd, Hangzhou, 310053, Zhejiang, China

    Wenhao Liang

Authors
  1. Huijun Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuanxiang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Maofu Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wenhao Liang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Huijun Hu.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Hu, H., Li, Y., Liu, M. et al. Classification of defects in steel strip surface based on multiclass support vector machine. Multimed Tools Appl 69, 199–216 (2014). https://doi.org/10.1007/s11042-012-1248-0

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-012-1248-0

Keywords

Search

Navigation