Technical Diagnostics and Non-Destructive Testing, 2024, №02



2024 №02 (03)

DOI of Article 10.37434/tdnk2024.02.04

2024 №02 (05)

---

Technical Diagnostics and Non-Destructive Testing #2, 2024, pp. 25-33

Methods for detecting surface defects on thin sheet materials for visual control automation (Review)

A.S. Novodranov

E.O. Paton Electric Welding Institute of the NAS of Ukraine 11 Kazymyr Malevych Str., 03150, Kyiv, Ukraine. E-mail: office@paton.kiev.ua

The use of methods for recognizing surface defects in order to automate the process of visual non-destructive control in production of rolled thin-sheet materials is becoming an increasingly urgent task. The use of automated systems for recognizing surface defects leads to early detection of damage and determination of their class and level of danger. After classifying the defect, the system makes a decision on further actions without the operator participation. Presence of such systems prevents equipment downtime and reduces the impact of the human factor on production. The classifier performance metrics was determined and analysis of the current techniques for identifying surface flaws was performed. The advantages and disadvantages of the methods are determined. The feasibility of using the method was analyzed depending on the type of surface and geometric characteristics of the defect. The expediency of using several methods to ensure more accurate recognition of surface defects is determined. Significant prospects for the application of machine learning methods based on neural networks are noted. The prospect of using neural networks in systems for automated recognition of surface defects is due to the possibility of automatic selection of features from the image, as well as processing of complex structures. 32 Ref., 1 Tabl., 7 Fig.
Keywords: surface defects, defect detection methods, sheet materials, automated monitoring, defect recognition, image processing

Received: 26.03.2024
Received in revised form: 25.04.2024
Accepted: 30.05.2024

References

1. Lv, X., Duan, F., Jiang, J., Fu, X., Gan, L. (2020) Deep metallic surface defect detection: The new benchmark and detection network. Sensors, 20, 1562. https://doi.org/10.3390/s20061562
2. Lv, X., Duan, F., Jiang, J., Fu, X., Gan, L. (2020) Deep active learning for surface defect detection. Sensors, 20, 1650. https://doi.org/10.3390/s20061650
3. Ghorai, S., Mukherjee, A., Gangadaran, M., Dutta, P.K. (2013) Automatic defect detection on hot-rolled flat steel products. IEEE Trans. Instrum. Meas., 62, 612-621. https://doi.org/10.1109/TIM.2012.2218677
4. Song, K., Yan, Y. (2013) A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects. Appl. Surf. Sci., 285, 858-864. https://doi.org/10.1016/j.apsusc.2013.09.002
5. Luo, Q., He, Y. (2016) A cost-effective and automatic surface defect inspection system for hot-rolled flat steel. Robot. Comput. Integr. Manuf., 38, 16-30. https://doi.org/10.1016/j.rcim.2015.09.008
6. Medium https://miro.medium.com/v2/resize:fit:640/format: webp/1*GDR0plA0fmHHbk9lZoGPBg.png
7. Alaa Tharwat (2020) Classification assessment methods. Applied Computing and Informatics, 17, 168-192. https://doi.org/10.1016/j.aci.2018.08.003
8. Xuewu, Z., Fang, G., Lizhong, X. (2012) Inspection of surface defects in copper strip using multivariate statistical approach and SVM. Int. J. Comput. Appl. Technol., 43, 44-50. https://doi.org/10.1504/IJCAT.2012.045840
9. Shi, T., Kong, J., Wang, X., Liu, Z., Zheng, G. (2016) Improved sobel algorithm for defect detection of rail surfaces with enhanced efficiency and accuracy. J. Cent. South. Univ., 23, 2867-2875. https://doi.org/10.1007/s11771-016-3350-3
10. Borselli, A., Colla, V., Vannucci, M., Veroli, M. (2010) A fuzzy inference system applied to defect detection in flat steel production. In: Proc. of the IEEE Int. Conf. on Fuzzy Systems, Barcelona, Spain, 1-6. https://doi.org/10.1109/FUZZY.2010.5584036
11. Shen, Y. (2010) Techniques of machine vision applied in detection of copper strip surface's defects. Electron. Meas. Technol., 33, 65-67. https://doi.org/10.1007/978-3-642-15621-2_34
12. Huang, X., Luo, X. (2014) A real-time algorithm for aluminum surface defect extraction on non-uniform image from CCD camera. In: Proc. of the Int. Conf. on Machine Learning and Cybernetics (ICMLC), Lanzhou, China, 556-561. https://doi.org/10.1109/ICMLC.2014.7009668
13. Ojala, T., Pietikainen, M., Harwood, D. (1996) A comparative study of texture measures with classification based on feature distributions. Pattern Recognit., 29, 51-59. https://doi.org/10.1016/0031-3203(95)00067-4
14. Song, K.C., Yan, Y.H., Chen, W.H., Zhang, X. (2013) Research and perspective on local binary pattern. Acta Automatica Sinica, 39, 730-744. https://doi.org/10.1016/S1874-1029(13)60051-8
15. Liao, S., Zhu, X., Lei, Z., Zhang, L., Li, S.Z. (2007) Learning multi-scale block local binary patterns for face recognition. In: Proc. of the Int. Conf. on Biometrics, Seoul, Korea, 828- 836. https://doi.org/10.1007/978-3-540-74549-5_87
16. Sharifzadeh, M., Alirezaee, S., Amirfattahi, R., Sadri, S. (2008) Detection of steel defect using the image processing algorithms. In: Proc. of the Inmic: Int. Multitopic Conf., 12th IEEE Int. Multitopic Conf., Karachi, Pakistan, 125-127. DOI: http://dx.doi.org/10.1109/INMIC.2008.4777721 https://doi.org/10.1109/INMIC.2008.4777721
17. Bulnes, F.G., Garcia, D.F., Javier de la Calle, F., Usamentiaga, R., Molleda, J. (2016) A non-invasive technique for online defect detection on steel strip surfaces. J. Nondestruct. Eval., 35, 1-18. https://doi.org/10.1007/s10921-016-0370-8
18. Tsai, D.-M., Chen, M.-C., Li, W.-C., Chiu, W.-Y. (2012) A fast regularity measure for surface defect detection. Mach. Vis. Appl., 23, 869-886. https://doi.org/10.1007/s00138-011-0403-3
19. Choi, J., Kim, C. (2012) Unsupervised detection of surface defects: A two-step approach. In: Proc. of the 19th IEEE Int. Conf. on Image Processing (ICIP), Lake Buena Vista, FL, USA, 1037-1040. https://doi.org/10.1109/ICIP.2012.6467040
20. Djukic, D., Spuzic, S. (2007) Statistical discriminator of surface defects on hot rolled steel. Proc. of Image and Vision Computing New Zealand 2007, 158-163.
21. Ai, Y., Xu, K. (2013) Surface detection of continuous casting slabs based on curvelet transform and kernel locality preserving projections. J. Iron Steel Res. Int., 20, 80-86. https://doi.org/10.1016/S1006-706X(13)60102-8
22. Paulraj, M.P., Shukry, A.M.M., Yaacob, S., Adom, A.H., Krishnan, R.P. (2010) Structural steel plate damage detection using DFT spectral energy and artificial neural network. In: Proc. of the 6th Int. Colloquium on Signal Processing & its Applications, Mallaca City, Malaysia, 1-6. https://doi.org/10.1109/CSPA.2010.5545247
23. Wu, X., Xu, K., Xu, J. (2008) Application of undecimated wavelet transform to surface defect detection of hot rolled steel plates. In: Proc. of the 1st Int. Congress on Image and Signal Processing, Sanya, China, 528-532. https://doi.org/10.1109/CISP.2008.278
24. Li, X., Tso, S.K., Guan, X., Huang, Q. (2006) Improving automatic detection of defects in castings by applying wavelet technique. IEEE Trans. Ind. Electron., 53, 1927-1934. https://doi.org/10.1109/TIE.2006.885448
25. Choi, D.C., Jeon, Y.J., Yun, J.P., Kim, S.W. (2011) Pinhole detection in steel slab images using Gabor filter and morphological features. Appl. Opt., 50, 5122-5129. https://doi.org/10.1364/AO.50.005122
26. Chol, D.C., Jeon, Y.J., Kim, S.H., Moon, S., Yun, J.P., Kim, S.W. (2017) Detection of pinholes in steel slabs using gabor filter combination and morphological features. ISIJ Int., 57, 1045-1053. https://doi.org/10.2355/isijinternational.ISIJINT-2016-160
27. Amirhossein Yazdani Abyaneh, Ali Hosein Gharari Foumani, Vahid Pourahmadi (2018) Deep Neural Networks Meet CSI-Based Authentication. DOI: https://doi.org/10.48550/arXiv.1812.04715
28. Kang, G.W., Liu, H.B. (2005) Surface defects inspection of cold rolled strips based on neural network. In: Proc. of the 4th Int. Conf. Machine Learning Cybernetics, Canton, China, 5034-5037. DOI: https://doi.org/10.1109/ICMLC. 2005.1527830
29. Chen, F., Jahanshahi, M.R. (2018) NB-CNN: Deep learning-based crack detection using convolutional neural network and naive bayes data fusion. IEEE Trans. Ind. Electron., 65, 4392-4400. https://doi.org/10.1109/TIE.2017.2764844
30. Bulnes, F.G., Usamentiaga, R., Garcia, D.F., Molleda, J. (2012) Vision-based sensor for early detection of periodical defects in web materials. Sensors, 12, 10788-10809. https://doi.org/10.3390/s120810788
31. James Lindsay, Sidney Gigivi (2020) A Novel way of Training a Neural Network with Reinforcement Learning and without Back Propagation. In: 2020 Int. Joint Conf. on Neural Networks (IJCNN). https://doi.org/10.1109/IJCNN48605.2020.9207659
32. Seyed Sajad Mousavi, Michael Schukat, Enda Howley (2017) Deep Reinforcement Learning: An Overview. In: Proc. of SAI Intelligent Systems Conf. https://doi.org/10.1007/978-3-319-56991-8_32

---

Advertising in this issue:

---