|Table of Contents|

[1] Wang Shuo, Zhang Liaojun, Yin Guojiang,. Defect identification method for steel surfaces based on improved YOLOv5 [J]. Journal of Southeast University (English Edition), 2024, 40 (1): 49-57. [doi:10.3969/j.issn.1003-7985.2024.01.006]

Defect identification method for steel surfaces based on improved YOLOv5()

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

2024 1
Research Field:
Computer Science and Engineering
Publishing date:


Defect identification method for steel surfaces based on improved YOLOv5
Wang Shuo1 Zhang Liaojun2 Yin Guojiang3
1 College of Civil and Transportation Engineering, Hohai University, Nanjing 210098, China
2 College of Water Conservancy and Hydropower Engineering, Hohai University, Nanjing 210098, China
3 Safety Testing Center of Hydraulic Metal Structure of the Ministry of Water Resources, Hohai University, Nanjing 210098, China
steel defect detection convolutional neural network You Only Look Once(YOLO)
Traditional machine vision detection methods suffer from low accuracy in identifying small-scale defects. To address this, a nondestructive identification method for steel surface defects is proposed based on an enhanced version of the fifth version of the You Only Look Once(YOLOv5)algorithm. In this improved approach, the Res2Block module is incorporated into the backbone of the YOLOv5 algorithm to expand the receptive field and improve computational efficiency. Additionally, the recursive gated convolution structure is fused into the neck of the YOLOv5 algorithm to further enhance the computational performance of the surface defect identification method. To validate the effectiveness of the proposed method, a series of ablation experiments were conducted using different module combinations. These results were then compared with those obtained through other object detection methods. This comparison reveals that the proposed method achieves a mean average precision of 67.8% and an F1-score of 86.0% in steel surface defect identification. When compared with the original YOLOv5 algorithm, the proposed method exhibits superior performance, particularly in the identification of small-scale steel surface defects. Furthermore, it also surpasses other object detection methods, such as SSD, YOLOv3, YOLOv5-Lite, and YOLOv8, demonstrating significant improvements in computational accuracy.


[1] Hu X J, Yang J, Jiang F L, et al. Steel surface defect detection based on self-supervised contrastive representation learning with matching metric[J].Applied Soft Computing, 2023, 145: 110578. DOI: 10.1016/j.asoc.2023.110578.
[2] Zhang S Y, Zhang Q J, Gu J F, et al. Visual inspection of steel surface defects based on domain adaptation and adaptive convolutional neural network[J].Mechanical Systems and Signal Processing, 2021, 153: 107541. DOI: 10.1016/j.ymssp.2020.107541.
[3] Roy A M, Bhaduri J. Dense SPH-YOLOv5: An automated damage detection model based on DenseNet and Swin-Transformer prediction head-enabled YOLOv5 with attention mechanism[J]. Advanced Engineering Informatics, 2023, 56: 102007. DOI: 10.1016/j.aei.2023.102007.
[4] Ni Y H, Lu H, Ji C, et al. Comparative analysis on bridge corrosion damage detection based on semantic segmentation[J]. Journal of Southeast University(Natural Science Edition), 2023, 53(2): 201-209. DOI:10.3969/j.issn.1001-0505.2023.02.003. (in Chinese)
[5] Gao Y P, Gao L, Li X Y. A hierarchical training-convolutional neural network with feature alignment for steel surface defect recognition[J].Robotics and Computer-Integrated Manufacturing, 2023, 81: 102507. DOI: 10.1016/j.rcim.2022.102507.
[6] Xing J J, Jia M P. A convolutional neural network-based method for workpiece surface defect detection[J]. Measurement, 2021, 176: 109185. DOI: 10.1016/j.measurement.2021.109185.
[7] Liu R Q, Huang M, Gao Z M, et al. MSC-DNet: An efficient detector with multi-scale context for defect detection on strip steel surface[J]. Measurement, 2023, 209: 112467. DOI: 10.1016/j.measurement.2023.112467.
[8] Zhao W D, Chen F, Huang H C, et al. A new steel defect detection algorithm based on deep learning[J].Computational Intelligence and Neuroscience, 2021, 2021: 5592878. DOI: 10.1155/2021/5592878.
[9] Wang S, Xia X J, Ye L Q, et al. Automatic detection and classification of steel surface defect using deep convolutional neural networks[J].Metals, 2021, 11(3): 388. DOI: 10.3390/met11030388.
[10] Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas, NV, USA, 2016: 779-788. DOI: 10.1109/CVPR.2016.91.
[11] Yin Z W, Shao J Y, Zhang N. YOLO-DAW: Object detection model based on dual attention mechanism within windows[J]. Journal of Southeast University(Natural Science Edition), 2023, 53(4): 718-724. DOI:10.3969/j.issn.1001-0505.2023.04.019. (in Chinese)
[12] Yuan T, Zhao X, Liu R, et al. Speed prediction model at urban intersections considering traffic participants[J].Journal of Southeast University(Natural Science Edition), 2023, 53(2): 326-333. DOI:10.3969/j.issn.1001-0505.2023.02.016. (in Chinese)
[13] Zhao C, Shu X, Yan X, et al. RDD-YOLO: A modified YOLO for detection of steel surface defects[J].Measurement, 2023, 214: 112776. DOI: 10.1016/j.measurement.2023.112776.
[14] Guo Z X, Wang C S, Yang G, et al. MSFT-YOLO: Improved YOLOv5 based on transformer for detecting defects of steel surface[J].Sensors, 2022, 22(9): 3467. DOI: 10.3390/s22093467.
[15] Liao D H, Cui Z H, Zhu Z X, et al. A nondestructive recognition and classification method for detecting surface defects of Si3N4 bearing balls based on an optimized convolutional neural network[J]. Optical Materials, 2023, 136: 113401. DOI: 10.1016/j.optmat.2022.113401.
[16] Gao S H, Cheng M M, Zhao K, et al. Res2Net: A new multi-scale backbone architecture[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(2): 652-662. DOI: 10.1109/TPAMI.2019.2938758.
[17] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA, 2016: 770-778. DOI: 10.1109/CVPR.2016.90.
[18] Rao Y M, Zhao W L, Tang Y S, et al.HorNet: Efficient high-order spatial interactions with recursive gated convolutions[EB/OL].(2022-07-28)[2023-03-18]. http://arxiv.org/abs/2207.14284.pdf.
[19] Zhou X, Hao W J, Bian C G, et al. Detection method for welding defects of YOLOv5 steel pipe based on gnConv and GAM[J]. Microelectronics & Computer, 2023, 40(9): 29-37. DOI:10.19304/J.ISSN1000-7180.2022.0778. (in Chinese)
[20] Chen Y, Zhou F C, Zhang J J, et al. Railway panoramic segmentation based on recursive gating enhancement and pyramid prediction[J/OL].(2023-10-07)[2023-11-11].Journal of Beijing University of Aeronautics and Astronautics. https://bhxb.buaa.edu.cn/bhzk/en/article/doi/10.13700/j.bh.1001-5965.2023.0492. DOI:10.13700/j.bh.1001-5965.2023.0492. (in Chinese)
[21] Zheng Z H, Wang P, Liu W, et al. Distance-IoU loss: Faster and better learning for bounding box regression[J].Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 12993-13000. DOI: 10.1609/aaai.v34i07.6999.
[22] Yun S, Han D, Chun S, et al.CutMix: Regularization strategy to train strong classifiers with localizable features[C]//2019 IEEE/CVF International Conference on Computer Vision(ICCV). Seoul, South Korea, 2019: 6022-6031. DOI: 10.1109/ICCV.2019.00612.


Biographies: Wang Shuo(1992—), female, doctor; Zhang Liaojun(corresponding author), male, doctor, professor, ljzhang@hhu.edu.cn.
Foundation items: The Natural Science Foundation of Jiangsu Province(No. BK20230956), the Jiangsu Funding Program for Excellent Postdoctoral Talents(No. 2022ZB188), the Transportation Technology Plan Project of Jiangsu Province(No. 2020QD28).
Citation: Wang Shuo, Zhang Liaojun, Yin Guojiang. Defect identification method for steel surfaces based on improved YOLOv5[J].Journal of Southeast University(English Edition), 2024, 40(1):49-57.DOI:10.3969/j.issn.1003-7985.2024.01.006.
Last Update: 2024-03-20