Automated Surface Defect Detection in Copper Blanks Using YOLOv8 Segmentation and EfficientNetV2-S Classification

Ghayoumi Zadeh, Hossein; Fayazi, Ali; Rezaee, Khosro; Aminaee, Afsaneh; Halavati, Hadi; Tahernejad, Mehdi; Memarzadeh, Hadi; Masoumi, Ali; Jafari, Mohammad Sadegh

doi:10.22044/jadm.2026.16853.2818

Articles in Press

Document Type : Review Article

Authors

¹ Department of Electrical Engineering, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran.

² Department of Electrical Engineering, Faculty of Engineering, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran

³ Department of Biomedical Engineering, Meybod University, Meybod, Iran

⁴ Director of Training and Competency Development, Sarcheshmeh Copper Complex, Rafsanjan, Iran.

⁵ Research and Development Division, Sarcheshmeh Copper Complex, Rafsanjan, Iran.

⁶ Technical and Engineering Research, Research and Development Department, Sarcheshmeh Copper Complex, Rafsanjan, Iran.

⁷ Head of Operations, Refinery and Casting Division, Sarcheshmeh Copper Complex, Rafsanjan, Iran.

⁸ Expert, Refinery and Casting Division, Sarcheshmeh Copper Complex, Rafsanjan, Iran

10.22044/jadm.2026.16853.2818

Abstract

In this study, an intelligent deep learning–based system is proposed for automated detection of surface defects in copper cathode blanks used in the electrorefining process. The proposed pipeline combines a YOLOv8-based segmentation model with an EfficientNetV2-S classifier to localize and analyze defect-relevant regions of each blank. The segmentation module identifies the main copper regions, edge strips, and defect-prone areas associated with surface anomalies such as scratches, dents, misalignment, and discoloration, effectively reducing background interference and improving classification reliability. The dataset includes 5,266 labeled images with a significant class imbalance, addressed using focal loss and class weighting during training. Experimental results on the test set demonstrate strong performance, achieving 98.32% accuracy, 96.71% precision, 95.67% recall, an F1-score of 96.19%, and an AUC of 0.9953. Grad-CAM visualizations and error analysis further confirm that the model consistently focuses on meaningful defect regions while remaining robust to background and illumination variations. These results highlight the effectiveness of the proposed approach for reliable quality control in industrial copper electrorefining lines.

Keywords

Main Subjects

H.6.5.7. Industry

References

[1] J. Hait, R. Jana, and S. Sanyal, “Processing of copper electrorefining anode slime: A review,” Mineral Processing and Extractive Metallurgy, vol. 118, no. 4, pp. 240–252, 2009.

[2] R. Moskalyk and A. Alfantazi, “Review of copper pyrometallurgical practice: today and tomorrow,” Minerals Engineering, vol. 16, no. 10, pp. 893-919, 2003.

[3] A. Artzer, M. Moats, and J. Bender, “Removal of antimony and bismuth from copper electrorefining electrolyte: Part I—A review,” JOM, vol. 70, no. 10, pp. 2033–2040, Oct. 2018.

[4] J. Djokić, A. M. Alfantazi, R. Moskalyk, and M. Moats, “Influence of electrolyte impurities from e-waste electrorefining on copper extraction recovery,” Metals, vol. 11, no. 9, Art. No. 1383, Sep. 2021.

[5] P. T. Smelting, “Electrolytic refining (ISA process),” May 2025. [Online]. Available: http://www.ptsmelting.com/e-re-isa.html [Accessed: May 29, 2025].

[6] J. Lu, Y. Wang, Z. Li, X. Zhang, and H. Liu, “Effect of rapid hollow cathode plasma nitriding treatment on corrosion resistance and friction performance of AISI 304 stainless steel,” Materials, vol. 16, no. 24, Art. No. 7616, Dec. 2023.

[7] K. R. Ahmed, “DSteelNet: A real-time parallel dilated convolutional neural network with atrous spatial pyramid pooling for detecting and classifying defects in surface steel strips,” Sensors, vol. 23, no. 1, Art. No. 544, Jan. 2023.

[8] Y. Xian, H. Zhang, Z. Liu, J. Wang, and L. Li, “YOT-Net: YOLOv3 combined triplet loss network for copper elbow surface defect detection,” Sensors, vol. 21, no. 21, Art. No. 7260, Nov. 2021.

[9] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, Jun. 2017.

[10] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv: 1409.1556, 2014.

[11] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, pp. 1–9, 2015.

[12] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770–778, 2016.

[13] G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 4700–4708, 2017.

[14] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “SSD: Single Shot MultiBox Detector,” in Computer Vision – ECCV 2016 (Lecture Notes in Computer Science, vol. 9905), pp. 21–37, 2016.

[15] R. Wei and Y. Bi, “Research on recognition technology of aluminum profile surface defects based on deep learning,” Materials, vol. 12, no. 10, Art. no. 1681, 2019.

[16] B. Hu and J. Wang, “Detection of PCB surface defects with improved Faster-RCNN and feature pyramid network,” IEEE Access, vol. 8, pp. 108335–108345, 2020.

[17] W. Zhao, F. Chen, H. Huang, D. Li, and W. Cheng, “A new steel defect detection algorithm based on deep learning,” Computational Intelligence and Neuroscience, vol. 2021, Art. No. 5592878, 2021.

[18] F. Huang, B.-w. Wang, Q.-p. Li, and J. Zou, “Texture surface defect detection of plastic relays with an enhanced feature pyramid network,” Journal of Intelligent Manufacturing, vol. 34, no. 3, pp. 1409–1425, 2023.

[19] X. Chen, J. Lv, Y. Fang, and S. Du, “Online detection of surface defects based on improved YOLOV3,” Sensors, vol. 22, no. 3, Art. No. 817, 2022.

[20] Y. Xie, W. Hu, S. Xie, and L. He, “Surface defect detection algorithm based on feature-enhanced YOLO,” Cognitive Computation, vol. 15, no. 2, pp. 565–579, 2023.

[21] H. Huang, X. Tang, F. Wen, and X. Jin, “Small object detection method with shallow feature fusion network for chip surface defect detection,” Scientific Reports, vol. 12, no. 1, Art. no. 3914, 2022.

[22]B. Fan and W. Li, “Application of GCB-net based on defect detection algorithm for steel plates,” Research square, 2022.

[23] Y. Ma, J. Yin, F. Huang, and Q. Li, “Surface defect inspection of industrial products with object detection deep networks: a systematic review,” Artificial Intelligence Review, vol. 57, no. 12, 2024.

[24] Z. Zhang, X. Huang, D. Wei, Q. Chang, J. Liu, and Q. Jing, “Copper nodule defect detection in industrial processes using deep learning,” Information, vol. 15, no. 12, Art. No. 802, 2024.

[25] G. Zhang, T. Chen, and J. Wang, “CSC-YOLO: An image recognition model for surface defect detection of copper strip and plates,” Journal of Shanghai Jiaotong University (Science), vol. 30, pp. 1037–1049, 2025.

[26] H. Zhao, J. Liu, X. Liu, Y. Shi, and Y. Qiao, “LSD-YOLOv5: A steel strip surface defect detection algorithm based on lightweight network and enhanced feature fusion mode,” Sensors, vol. 23, no. 14, Art. no. 6558, 2023.

[27] C. Zhao, Y. Liu, H. Zhang, J. Wang, and X. Li, “RDD-YOLO: A modified YOLO for detection of steel surface defects,” Measurement, vol. 214, Art. No. 112776, 2023.

[28] J. Shi, J. Yang, and Y. Zhang, “Research on steel surface defect detection based on YOLOv5 with attention mechanism,” Electronics, vol. 11, no. 22, Art. no. 3735, 2022.

[29] Z. Guo, Y. Liu, Y. Zhang, X. Wang, and J. Sun, “MSFT-YOLO: Improved YOLOv5 based on transformer for detecting defects of steel surface,” Sensors, vol. 22, no. 9, Art. no. 3467, 2022.

[30] L. Li, Y. Wang, X. Zhao, Z. Liu, and H. Chen, “The bearing surface defect detection method combining magnetic particle testing and deep learning,” Applied Sciences, vol. 14, no. 5, Art. no. 1747, 2024.

[31] Y. Xia, J. Xiao, and Y. Weng, “Surface defect detection of polarizer based on improved Faster R-CNN,” Optical Techniques, vol. 47, no. 6, pp. 695–702, 2021.

[32] Y. Xian, H. Zhang, Z. Liu, J. Wang, and X. Li, “An EA-based pruning on improved YOLOv3 for rapid copper elbow surface defect detection,” Engineering Applications of Artificial Intelligence, vol. 123, Art. No. 106412, 2023.

[33] B. Zhou, H. Chen, J. Luo, P. Li, B. Xiang, and K. Li, “AEB-YOLO: An efficient multi-scale defect detection algorithm for copper strips,” AIP Advances, vol. 15, no. 9, Art. No. 095310, 2025.

[34] L. Zhang, Z. Wang, Y. Ma, and G. Li, “Steel surface defect detection algorithm based on improved YOLOv10,” Scientific Reports, vol. 15, Art. No. 32827, 2025.

[35] J. Cao, Z. Wang, Y. Wang, X. Ma, and H. Li, “A graph-based approach for module library development in industrialized construction,” Computers in Industry, vol. 139, Art. No. 103659, 2022.

[36] Y. Fang, L. Sun, Z. Wang, and J. Chen, “Modulation of porphyrin photoluminescence by nanoscale spacers on silicon substrates,” Applied Surface Science, vol. 285, pp. 572–576, 2013.

[37] D. Ma, Y. Liu, X. Chen, J. Zhang, and Z. Wang, “Multi-sensing signals diagnosis and CNN-based detection of porosity defect during Al alloys laser welding,” Journal of Manufacturing Systems, vol. 62, pp. 334–346, 2022.

[38] M. Bellaoui, K. Bouchouicha, and I. Oulimar, “Estimation of daily global solar radiation based on MODIS satellite measurements: The case study of Adrar region (Algeria),” Measurement, vol. 183, Art. No. 109802, 2021.

[39] M. Tan and Q. V. Le, “EfficientNetV2: Smaller models and faster training,” in Proceedings of the International Conference on Machine Learning (ICML), pp. 10096–10106, 2021.

[40] S. A. Amiri and Z. Davoudi, "Enhanced Deep Learning Approaches for Wildfire Detection Using Satellite Imagery," Journal of AI and Data Mining, vol. 13, no. 4, pp. 491–500, Oct. 2025.

Automated Surface Defect Detection in Copper Blanks Using YOLOv8 Segmentation and EfficientNetV2-S Classification

References

References

Articles in Press, Accepted Manuscript Available Online from 14 February 2026

Articles in Press, Accepted Manuscript
Available Online from 14 February 2026