Skip to main content
SpringerLink
Log in

A semi-supervised learning method for surface defect classification of magnetic tiles

  • Original Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

Surface defect inspection is a crucial step to ensure the quality of magnetic tiles. Recently, deep learning methods have shown excellent performance on many vision tasks. Some deep learning-based methods have been applied to the surface defect inspection of magnetic tiles as well. However, related methods are based on supervised learning, which requires plenty of labeled samples to train deep neural networks. In industrial application scenarios, the annotation of large labeled datasets is extremely expensive, time-consuming, and error-prone. A semi-supervised learning method based on pseudo-labeling is proposed in this paper to address the problem of surface defect classification of magnetic tiles with limited labeled samples. The proposed method consists of two models: the teacher model and the student model. The training procedure is divided into two stages: pseudo-label generation and student model training. In the pseudo-label generation stage, the teacher model parameters and the pseudo-labels of unlabeled samples are alternatively optimized based on the idea of transductive learning. Curriculum learning is employed to reduce the impact of label noise so that high-quality pseudo-labels can be obtained. In the student model training stage, labeled samples and unlabeled samples with pseudo-labels are jointly used to train the classifier, with mixup to achieve information fusion and regularization. The experimental results show that the proposed method outperforms the supervised-only and semi-supervised baselines. With only 4.4% of labeled samples in the training set, the proposed method can still achieve the defect classification accuracy of 90.13%.

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
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

References

  1. Tao J., Wang Y., Wang K.: Defect detection for end surface of ferrite magnetic tile. In: 8th Int. Symp. AOMATT, 9684 513–520, https://doi.org/10.1117/12.2241044. Sep. 2016

  2. Yang, C., Liu, P., Yin, G., Jiang, H., Li, X.: Defect detection in magnetic tile images based on stationary wavelet transform. NDT E Int. 83, 78–87 (2016). https://doi.org/10.1016/j.ndteint.2016.04.006

    Article  Google Scholar 

  3. Li, X., Jiang, H., Yin, G.: Detection of surface crack defects on ferrite magnetic tile. NDT E Int. 62, 6–13 (2014). https://doi.org/10.1016/j.ndteint.2013.10.006

    Article  Google Scholar 

  4. Xie, L., Lin, L., Yin, M., Meng, L., Yin, G.: A novel surface defect inspection algorithm for magnetic tile. Appl. Surf. Sci. 375, 118–126 (2016). https://doi.org/10.1016/j.apsusc.2016.03.013

    Article  Google Scholar 

  5. Huang, Y., Qiu, C., Yuan, K.: Surface defect saliency of magnetic tile. Vis. Comput. 36(1), 85–96 (2020). https://doi.org/10.1007/s00371-018-1588-5

    Article  MathSciNet  Google Scholar 

  6. Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. MICCAI 9351, 234–241 (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    Article  Google Scholar 

  7. Xie, L., Xiang, X., Huining, X., Wang, L., Lin, L., Yin, G.: FFCNN: A deep neural network for surface defect detection of magnetic tile. IEEE Trans. Ind. Electron. 68(4), 3506–3516 (2021). https://doi.org/10.1109/TIE.2020.2982115

    Article  Google Scholar 

  8. Cui, L., Jiang, X., Xu, M., Li, W., Lv, P., Zhou, B.: SDDNet: a fast and accurate network for surface defect detection. IEEE Trans. Instrum. Meas. 70, 1–13 (2021). https://doi.org/10.1109/TIM.2021.3056744

    Article  Google Scholar 

  9. Hajizadeh, S., Núñez, A., Tax, D.M.J.: Semi-supervised rail defect detection from imbalanced image data. IFAC-Pap. 49(3), 78–83 (2016). https://doi.org/10.1016/j.ifacol.2016.07.014

    Article  Google Scholar 

  10. Chun, C., Ryu, S.-K.: Road surface damage detection using fully convolutional neural networks and semi-supervised learning. Sensors 19(24), 5501 (2019). https://doi.org/10.3390/s19245501

    Article  Google Scholar 

  11. Gao, Y., Gao, L., Li, X., Yan, X.: A semi-supervised convolutional neural network-based method for steel surface defect recognition. Robot. Comput.-Integr. Manuf. 61, 101825 (2020). https://doi.org/10.1016/j.rcim.2019.101825

    Article  Google Scholar 

  12. He, Y., Song, K., Dong, H., Yan, Y.: Semi-supervised defect classification of steel surface based on multi-training and generative adversarial network. Opt. Lasers Eng. 122, 294–302 (2019). https://doi.org/10.1016/j.optlaseng.2019.06.020

    Article  Google Scholar 

  13. Di, H., Ke, X., Peng, Z., Dongdong, Z.: Surface defect classification of steels with a new semi-supervised learning method. Opt. Lasers Eng. 117, 40–48 (2019). https://doi.org/10.1016/j.optlaseng.2019.01.011

    Article  Google Scholar 

  14. Tao, X., et al.: Bearing defect diagnosis based on semi-supervised kernel Local fisher discriminant analysis using pseudo labels. ISA Trans. 110, 394–412 (2021). https://doi.org/10.1016/j.isatra.2020.10.033

    Article  Google Scholar 

  15. Zhang, S., Ye, F., Wang, B., Habetler, T.G.: Semi-supervised bearing fault diagnosis and classification using variational autoencoder-based deep generative models. IEEE Sens. J. 21(5), 6476–6486 (2021). https://doi.org/10.1109/JSEN.2020.3040696

    Article  Google Scholar 

  16. Liu, J., Song, K., Feng, M., Yan, Y., Tu, Z., Zhu, L.: Semi-supervised anomaly detection with dual prototypes autoencoder for industrial surface inspection. Opt. Lasers Eng. 136, 106324 (2021). https://doi.org/10.1016/j.optlaseng.2020.106324

    Article  Google Scholar 

  17. Wang, Y., Gao, L., Gao, Y., Li, X.: A new graph-based semi-supervised method for surface defect classification. Robot. Comput.-Integr. Manuf. 68, 102083 (2021). https://doi.org/10.1016/j.rcim.2020.102083

    Article  Google Scholar 

  18. Danlei, X., Fei, W., Ying, S., Xiao-Yuan, J.: Cross-project defect prediction via semi-supervised discriminative feature learning. IEICE Trans. Inf. Syst. E103.D(10), 2237–2240 (2020). https://doi.org/10.1587/transinf.2020EDL8044

    Article  Google Scholar 

  19. Ouali Y., Hudelot C., Tami M.: An overview of deep semi-supervised learning. https://arxiv.org/abs/2006.05278, Accessed: Jun. 23, 2020. [Online]. http://arxiv.org/abs/2006.05278. (2020)

  20. Lee, D.-H.: Pseudo-label : the simple and efficient semi-supervised learning method for deep neural networks. ICML Workshop Chall. Represent. Learn 3(2), 896 (2013)

    Google Scholar 

  21. Chapelle O., Zien A.: Semi-supervised classification by low density separation. In: Proc. 10th Int. Workshop AISTATS, Jan. 2005, [Online]. http://www.gatsby.ucl.ac.uk/aistats/fullpapers/198.pdf. (2005)

  22. Yves, G., Yoshua, B.: Entropy regularization. In: Chapelle, O., Scholkopf, B., Zien, A. (eds.) Semi-Supervised Learning, pp. 151–168. The MIT Press (2006)

    Chapter  Google Scholar 

  23. Zhang C., Bengio S., Hardt M., Recht B., Vinyals O.: Understanding deep learning requires rethinking generalization. [Online]. Available: https://openreview.net/forum?id=Sy8gdB9xx. (2017)

  24. Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  25. Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: ICML, pp. 41–48. NY, USA, New York (2009)

    Google Scholar 

  26. Zhang H., CisseM., Dauphin Y. N., Lopez-Paz D.: Mixup: Beyond empirical risk minimization. ICLR, Accessed: Mar. 12, 2020. [Online]. https://openreview.net/forum?id=r1Ddp1-Rb. (2018)

  27. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition, pp. 770–778. CVPR (2016)

    Google Scholar 

  28. Huang, G., Liu, Z., Maaten, L.V.D., Weinberger, K.Q.: Densely connected convolutional networks, pp. 2261–2269. CVPR (2017)

    Google Scholar 

  29. A. Tarvainen and H. Valpola, “Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results,” in NIPS, Feb. 2017, Accessed: Mar. 10, 2020. [Online]. https://openreview.net/forum?id=ry8u21rtl.

  30. Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.-C.: MobileNetV2: Inverted residuals and linear bottlenecks, pp. 4510–4520. CVPR, Salt Lake City UT, USA (2018)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Zhejiang University, Hangzhou, 310007, China

    Tao Liu & Wei Ye

Authors
  1. Tao Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wei Ye
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wei Ye.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, T., Ye, W. A semi-supervised learning method for surface defect classification of magnetic tiles. Machine Vision and Applications 33, 35 (2022). https://doi.org/10.1007/s00138-022-01286-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00138-022-01286-x

Keywords

Search

Navigation