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.
Similar content being viewed by others
References
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
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
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
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
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
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
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
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
Mohebbifar M, Omarmeli K (2020) Defect detection by combination of 605 threshold and multistep watershed techniques. Russ J Nondestr Test 56(1):80–91
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)
Miao Y, Jeon JY, Park G (2020) An image processing-based crack detection technique for pressed panel products. J Manuf Syst 57:287–297
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
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
Božič J, Tabernik D, Skočaj D (2021) Mixed supervision for surface-defect detection: from weakly to fully supervised learning. Comput Ind 129:103459
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
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
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
Huang G, Jafari AH (2021) Enhanced balancing GAN: minority-class image generation. Neural Comput Appl 35(7):5145–5154
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
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
Yuan D, Chang X, Huang P-Y, Liu Q, He Z (2020) Self-supervised deep correlation tracking. IEEE Trans Image Process 30:976–985
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
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
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
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
Sivakumar V, Janakiraman N (2020) A novel method for segmenting brain tumor using modified watershed algorithm in MRI image with FPGA. Biosystems 198:104226
Xing Y, Zhong L, Zhong X (2020) An encoder-decoder network based FCN architecture for semantic segmentation. Wirel Commun Mob Comput 2020:8861886
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
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
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
Li F, Xi Q (2021) Defectnet: toward fast and effective defect detection. IEEE Trans Instrum Meas 70:1–9
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
Authors and Affiliations
Corresponding author
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.
About this article
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
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-08600-2