Welcome to Francis Academic Press

Academic Journal of Materials & Chemistry, 2024, 5(3); doi: 10.25236/AJMC.2024.050317.

Steel surface defect detection based on improved YOLOv8 neural network

Author(s)

Siyi Wu1, Jiarui Li2, Zhongyi Zhao1, Zihao Wang3, Junxi Li4

Corresponding Author:
Junxi Li
Affiliation(s)

1Nanjing University of Science and Technology, Nanjing, China

2Xian University of Technology, Xi’an, China

3Peter the Great St. Petersburg Polytechnic University, St. Petersburg, Russian Federation

4Herzen University, St. Petersburg, Russian Federation

Abstract

In this study, we use a neural network approach instead of the traditional manual approach to solve the problem regarding the detection of defects on steel surfaces. We introduce several attention mechanisms to improve the Yolo v8 neural network trained on a steel defect detection dataset. The results show that our improved Yolo v8 model improves the robustness of the model more significantly and can detect more detailed steel surface defects.

Keywords

Attention Mechanism; Object Detection; Steel Surface Defects

Cite This Paper

Siyi Wu, Jiarui Li, Zhongyi Zhao, Zihao Wang, Junxi Li. Steel surface defect detection based on improved YOLOv8 neural network. Academic Journal of Materials & Chemistry (2024) Vol. 5, Issue 3: 110-116. https://doi.org/10.25236/AJMC.2024.050317.

References

[1] Chen Wanzhi, Zhang Chunguang. Improved YOLOv5 model for detecting surface defects on steel strip. Journal of Liaoning Technical University (Natural Science Edition)/Liaoning Gongcheng Jishu Daxue Xuebao (Ziran Kexue Ban), 2024, 43(3).

[2] Jain, S.; Seth, G.; Paruthi, A.; Soni, U.; Kumar, G. Synthetic data augmentation for surface defect detection and classification using deep learning. J. Intell. Manuf. 2020, 33, 1007–1020.

[3] Luo, Q.; Fang, X.; Su, J.; Zhou, J.; Zhou, B.; Yang, C.; Liu, L.; Gui, W.; Lu, T. Automated Visual Defect Classification for Flat Steel Surface: A Survey. IEEE Trans. Instrum. Meas. 2020, 69, 9329–9349.

[4] Dalal, N.; Triggs, B. Histograms of oriented gradients for human detection. In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA, 20–25 June 2005; IEEE: Piscatevi, NJ, USA, 2005; 1, pp. 886–893.

[5] Felzenszwalb, P.F.; Girshick, R.B.; McAllester, D.; Ramanan, D. Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 2010, 32, 1627–1645.

[6] Krizhevsky, A.; Sutskever, I.; Hinton, G.E. Imagenet classification with deep convolutional neural networks. Commun. ACM 2017, 60, 84–90.

[7] He, K.; Zhang, X.; Ren, S.; Sun, J. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 2015, 37, 1904–1916.

[8] Girshick, R. Fast r-cnn. In Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 7–13 December 2015; pp. 1440–1448.

[9] Ren, S.; He, K.; Girshick, R.; Sun, J. Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 2015, 28.

[10] Lin, T.Y.; Goyal, P.; Girshick, R.; He, K.; Dollár, P. Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 2980–2988. 

[11] Cai, Z.; Vasconcelos, N. Cascade r-cnn: Delving into high quality object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Los Alamitos, CA, USA, 18–22 June 2018; pp. 6154–6162.