Skip to main content
SpringerLink
Log in

Ingot oxide slag detection using two-stage UNet network based on mixed supervised learning

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

This paper presents a new method for detecting the amount of oxide slag on metal ingots, which is a critical indicator of the quality of the ingots. The challenge arises due to the irregular shape and small number of samples of the oxide slag, which makes it difficult to create a pixel-level label dataset for training a semantic segmentation network. To overcome this, a two-stage UNet network based on mixed supervised learning is proposed in this paper. The network uses a combination of a small number of pixel-level labels and a large number of weak label samples to reduce the cost of creating the dataset while achieving better detection accuracy. To solve the issue of overfitting due to the small number of samples, an improved generative adversarial network (GAN) is used to generate oxide slag images with arbitrary shapes to expand the dataset and improve the detection accuracy. Experiments show that the proposed network is highly effective in accurately detecting the distribution of oxide slag on metal ingots. Compared to existing segmentation algorithms, the network achieves higher accuracy while requiring a lower cost for dataset creation. The results of this work have important implications for the practical application of intelligent sensing in slag-picking robots.

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

Similar content being viewed by others

References

  1. Samhouri M, Al-Arabiat L, Al-Atrash F (2022) Prediction and measurement of damage to architectural heritages facades using convolutional neural networks. Neural Comput Appl 34(20):18125–18141

    Article  Google Scholar 

  2. Hua S, Xu M, Xu Z, Ye H, Zhou C (2022) Multi-feature decision fusion algorithm for disease detection on crop surface based on machine vision. Neural Comput Appl 34(12):9471–9484

    Article  Google Scholar 

  3. Wang C, Wang N, Ho S-C, Chen X, Song G (2019) Design of a new vision-based method for the bolts looseness detection in flange connections. IEEE Trans Ind Electron 67(2):1366–1375

    Article  Google Scholar 

  4. Wang H, Zhang J, Tian Y, Chen H, Sun H, Liu K (2018) A simple guidance template-based defect detection method for strip steel surfaces. IEEE Trans Ind Inform 15(5):2798–2809

    Article  Google Scholar 

  5. Sun J, Li C, Wu X-J, Palade V, Fang W (2019) An effective method of weld defect detection and classification based on machine vision. IEEE Trans Ind Inform 15(12):6322–6333

    Article  Google Scholar 

  6. Mishra A, Singh UP, Singh KP (2023) A lightweight relation network for few-shots classification of hyperspectral images. Neural Comput Appl 35(15):11417–11430

    Article  Google Scholar 

  7. de la Calle Herrero FJ, García DF, Usamentiaga R (2018) Inspection system for rail surfaces using differential images. IEEE Trans Ind Appl 54(5):4948–4957

    Article  Google Scholar 

  8. Liu J, Zhou J, Tang Z, Gui W, Xie Y, He J, Ma T, Niyoyita JP (2019) Toward flotation process operation-state identification via statistical modeling of biologically inspired Gabor filtering responses. IEEE Trans Cybern 50(10):4242–4255

    Article  Google Scholar 

  9. Mohebbifar M, Omarmeli K (2020) Defect detection by combination of 605 threshold and multistep watershed techniques. Russ J Nondestr Test 56(1):80–91

    Article  Google Scholar 

  10. Aslam Y, Santhi N, Ramasamy N, Ramar K (2018) An effective surface defect detection method using adaptive thresholding fused with PSO algorithm. Int J Simul Syst Sci Technol 19(6)

  11. Miao Y, Jeon JY, Park G (2020) An image processing-based crack detection technique for pressed panel products. J Manuf Syst 57:287–297

    Article  Google Scholar 

  12. Liu Y, Xu J, Wu Y (2021) A CISG method for internal defect detection of solar cells in different production processes. IEEE Trans Ind Electron 69(8):8452–8462

    Article  Google Scholar 

  13. He Y, Song K, Meng Q, Yan Y (2019) An end-to-end steel surface defect detection approach via fusing multiple hierarchical features. IEEE Trans Instrum Meas 69(4):1493–1504

    Article  Google Scholar 

  14. Božič J, Tabernik D, Skočaj D (2021) Mixed supervision for surface-defect detection: from weakly to fully supervised learning. Comput Ind 129:103459

    Article  Google Scholar 

  15. Božič J, Tabernik D, Skočaj D (2021) End-to-end training of a two-stage neural network for defect detection. Proc Int Conf Pattern Recognit 2021:5619–5626

    Google Scholar 

  16. Le X, Mei J, Zhang H, Zhou B, Xi J (2020) A learning-based approach for surface defect detection using small image datasets. Neurocomputing 408:112–120

    Article  Google Scholar 

  17. Liu X, Zhang T, Zhang J (2022) Toward visual quality enhancement of dehazing effect with improved cycle-GAN. Neural Comput Appl 35(7):5277–5290

    Article  Google Scholar 

  18. Huang G, Jafari AH (2021) Enhanced balancing GAN: minority-class image generation. Neural Comput Appl 35(7):5145–5154

    Article  Google Scholar 

  19. Tabernik D, Šela S, Skvarč J, Skočaj D (2020) Segmentation-based deep-learning approach for surface-defect detection. J Intell Manuf 31(3):759–776

    Article  Google Scholar 

  20. Neuhauser FM, Bachmann G, Hora P (2020) Surface defect classification and detection on extruded aluminum profiles using convolutional neural networks. Int J Mater Form 13(4):591–603

    Article  Google Scholar 

  21. Yuan D, Chang X, Huang P-Y, Liu Q, He Z (2020) Self-supervised deep correlation tracking. IEEE Trans Image Process 30:976–985

    Article  Google Scholar 

  22. Yuan D, Chang X, Li Z, He Z (2022) Learning adaptive spatial-temporal context-aware correlation filters for UAV tracking. ACM Trans Multimed Comput Commun Appl (TOMM) 18(3):1–18

    Article  Google Scholar 

  23. Qian Y, Zhu H, Chen L, Zhou J (2021) Hyperspectral image restoration with self-supervised learning: a two-stage training approach. IEEE Trans Geosci Remote Sens 60:1–17

    Google Scholar 

  24. Xia X, Pan X, Li N, He X, Ma L, Zhang X, Ding N (2022) Gan-based anomaly detection: a review. Neurocomputing 493:497–535

    Article  Google Scholar 

  25. Cheng B, Schwing A, Kirillov A (2021) Per-pixel classification is not all you need for semantic segmentation. Adv Neural Inf Process Syst 34:17864–17875

    Google Scholar 

  26. Sivakumar V, Janakiraman N (2020) A novel method for segmenting brain tumor using modified watershed algorithm in MRI image with FPGA. Biosystems 198:104226

    Article  Google Scholar 

  27. Xing Y, Zhong L, Zhong X (2020) An encoder-decoder network based FCN architecture for semantic segmentation. Wirel Commun Mob Comput 2020:8861886

    Article  Google Scholar 

  28. He Y, Song K, Meng Q, Yan Y (2019) An end-to-end steel surface defect detection approach via fusing multiple hierarchical features. IEEE Trans Instrum Meas 69(4):1493–1504

    Article  Google Scholar 

  29. Su Y, Yan P, Yi R, Chen J, Hu J, Wen C (2022) A cascaded combination method for defect detection of metal gear end-face. J Manuf Syst 63:439–453

    Article  Google Scholar 

  30. Liu Z, Huo Z, Li C, Dong Y, Li B (2021) DLSE-net: a robust weakly supervised network for fabric defect detection. Displays 68:102008

    Article  Google Scholar 

  31. Li F, Xi Q (2021) Defectnet: toward fast and effective defect detection. IEEE Trans Instrum Meas 70:1–9

    Google Scholar 

Download references

Acknowledgements

This work is supported by the National Natural Science Foundation (No.61973320), the National Key Research and Development Program (No.2018YFB1309002), the joint fund of Liaoning Province State Key Laboratory of Robotics under grant number 2021KF2218, the Key Research Project of Hunan Province under grant number QL20210048 and the Fundamental Research Funds for the Central Universities of Central South University (No.1053320191942).

Author information

Author notes

  1. Chunhua Yang and Weihua Gui have contributed equally to this work.

Authors and Affiliations

  1. School of Automation, Central South University, Changsha, 410083, Hunan, China

    Jie Wu, Degang Xu, Chunhua Yang & Weihua Gui

  2. Engineering Research Center of Ministry of Education, Central South University, Changsha, 410083, Hunan, China

    Jie Wu, Degang Xu, Chunhua Yang & Weihua Gui

Authors
  1. Jie Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Degang Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chunhua Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Weihua Gui
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Degang Xu.

Ethics declarations

Conflict of interest

These no potential competing interests in our paper. And all authors have seen the manuscript and approved to submit to your journal. We confirm that the content of the manuscript has not been published or submitted for publication elsewhere.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Consent to participate

The authors voluntarily agree to participate in this research.

Consent for publication

The author gives the publisher license of the copyright which provides the publisher with an exclusive right to publish and sell the research findings in all languages, in whole or in part.

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wu, J., Xu, D., Yang, C. et al. Ingot oxide slag detection using two-stage UNet network based on mixed supervised learning. Neural Comput & Applic 35, 18277–18292 (2023). https://doi.org/10.1007/s00521-023-08600-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-023-08600-2

Keywords

Search

Navigation