Development of an Improved YOLOv7-Based Model for Detecting Defects on Strip Steel Surfaces
Source abstract
Abstract
The detection of defects on the surface is of great importance for both the production and the application of strip steel. In order to detect the defects accurately, an improved YOLOv7-based model for detecting strip steel surface defects is developed. To enhances the ability of the model to extract features and identify small features, the ConvNeXt module is introduced to the backbone network structure, and the attention mechanism is embedded in the pooling module. To reduce the size and improves the inference speed of the model, an improved C3 module was used to replace the ELAN module in the head. The experimental results show that, compared with the original models, the mAP of the proposed model reached 82.9% and improved by 6.6%. The proposed model can satisfy the need for accurate detection and identification of strip steel surface defects.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Advanced Neural Network Applications · Surface Roughness and Optical Measurements
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Teachers College for Vocational and Technical Education, Guangxi Normal University, Guilin 541004, China
Key Laboratory of AI and Information Processing, Hechi University, Hechi 546300, China
Funding
China University · Key Laboratory of AI and Information Processing · The Natural Science Foundation Project of Guangxi, China · The Key R&D Program Project of Guangxi, China · The basic ability improvement project for young and middle-aged teachers of universities in Guangxi, China
References (45)
Show source-provided references
1. Development of a YOLO-V3-based model for detecting defects on steel strip surface10.1016/j.measurement.2021.109454 ↗
2. Visual techniques for defects detection in steel products: A comparative study10.1016/j.engfailanal.2022.106047 ↗
3. Sun, B., Cheng, L., Du, C.-Y., Zhang, J.-K., He, Y.-Q., and Cao, G.-M. (2021). Effect of Oxide Scale Microstructure on Atmospheric Corrosion Behavior of Hot Rolled Steel Strip. Coatings, 11.10.3390/coatings11050517 ↗
4. Shi, H., Wang, J., and Li, Y. (2023). Small sample data enhancement method for strip steel based on improved ACGAN algorithm. Comput. Integr. Manuf. Syst., 1–12. Available online: https://kns.cnki.net/kcms/detail//11.5946.TP.20230104.1047.004.html.
5. A steel surface defect inspection approach towards smart industrial monitoring10.1007/s10845-020-01670-2 ↗
6. Strip steel surface defect detection method by improved YOLOv5 network
7. Liang, X., and Xiao, H. (2023). Lightweight strip defect real-time detection algorithm based on SDD-YOLO. China Meas. Test., 1–8. Available online: https://kns.cnki.net/kcms/detail//51.1714.TB.20230109.1648.002.html.
8. Hot-Rolled Steel Strip Surface Inspection Based on Transfer Learning Model10.1155/2021/6637252 ↗
9. Strip Steel Defect Classification Using the Improved GAN and EfficientNet10.1080/08839514.2021.1995231 ↗
10. Multi-class classification method for strip steel surface defects based on support vector machine with adjustable hyper-sphere10.1007/s42243-018-0103-6 ↗
11. Huang, X., Sun, S., Zhang, Y., Li, B., Ren, Y., and Zhao, L. (2023). Research on the detection method of surface defects of strip steel under uneven illumination. Mech. Sci. Technol. Aerosp. Eng., 1–8.
12. A fast regularity measure for surface defect detection10.1007/s00138-011-0403-3 ↗
13. Steel Surface Defect Detection Using a New Haar-Weibull-Variance Model in Unsupervised Manner10.1109/TIM.2017.2712838 ↗
14. Defect Detection of Steel Surfaces with Global Adaptive Percentile Thresholding of Gradient Image10.1007/s40031-017-0296-2 ↗
15. Differential evolution-based optimal Gabor filter model for fabric inspection10.1016/j.neucom.2015.09.011 ↗
16. Detection of Pinholes in Steel Slabs Using Gabor Filter Combination and Morphological Features10.2355/isijinternational.ISIJINT-2016-160 ↗
17. Surface Defect Detection via Entity Sparsity Pursuit with Intrinsic Priors10.1109/TII.2019.2917522 ↗
18. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
19. Ross, G. (2015, January 11–18). Fast R-CNN[A] in: Institute of Electrical and Electronics Engineers. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV 2015), Santiago, Chile.
20. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks10.1109/TPAMI.2016.2577031 ↗
21. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11–14). SSD: Single Shot MultiBox Detector. Proceedings of the Computer Vision—ECCV 2016: 14th European Conference, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
22. Focal Loss for Dense Object Detection10.1109/TPAMI.2018.2858826 ↗
23. Joseph, R., Santosh, D., Ross, G., and Ali, F. (July, January 26). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.
24. Joseph, R., and Ali, F. (2017, January 21–26). YOL09000: Better, Faster, Stronger. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, HI, USA.
25. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
26. Bochkovskiy, A., Wang, C., and Liao, H. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.
27. Jocher, G. (2021, April 12). YOLOv5 Release v5.0. Available online: https://github.com/ultralytics/yolov5/releases/tag/v5.0.
28. Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). YOLOX: Exceeding YOLO Series in 2021. arXiv.
29. Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., and Wei, X. (2022). YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications. arXiv.
30. Wang, C.Y., Bochkovskiy, A., and Liao, H. (2021). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv.
31. Wang, S., Xia, X., Ye, L., and Yang, B. (2021). Automatic Detection and Classification of Steel Surface Defect Using Deep Convolutional Neural Networks. Met.-Open Access Metall. J., 11.10.3390/met11030388 ↗
32. He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.10.1109/CVPR.2016.90 ↗
33. Surface defect detection of steel strips based on improved YOLOv410.1016/j.compeleceng.2022.108208 ↗
34. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv.
35. Guo, Z., Wang, C., Yang, G., Huang, Z., and Li, G. (2022). MSFT-YOLO: Improved YOLOv5 Based on Transformer for Detecting Defects of Steel Surface. Sensors, 22.10.3390/s22093467 ↗
36. Lee, Y., Hwang, J.-W., Lee, S., Bae, Y., and Park, J. (2019, January 16–17). An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2019), Long Beach, CA, USA.10.1109/CVPRW.2019.00103 ↗
37. Wang, C.-Y., Bochkovskiy, A., and Liao, H.-Y.M. (2021, January 19–25). Scaled-YOLOv4: Scaling Cross Stage Partial Network. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), Virtual Conference.10.1109/CVPR46437.2021.01283 ↗
38. Wang, C.-Y., Liao, H.-Y.M., and Yeh, I.-H. (2022). Designing Network Design Strategies Through Gradient Path Analysis. arXiv.
39. Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022). A ConvNet for the 2020s. arXiv.10.1109/CVPR52688.2022.01167 ↗
40. Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021). Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. arXiv.10.1109/ICCV48922.2021.00986 ↗
41. Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K. (2017). Aggregated Residual Transformations for Deep Neural Networks. arXiv.10.1109/CVPR.2017.634 ↗
42. Diganta, M. (2019). Mish: A Self Regularized Non-Monotonic Activation Function. arXiv.
43. Woo, S., Park, J., Lee, J.-Y., and Kweon, I.S. (2018). CBAM: Convolutional Block Attention Module. arXiv.10.1007/978-3-030-01234-2_1 ↗
44. Squeeze-and-Excitation Networks10.1109/TPAMI.2019.2913372 ↗
45. A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects10.1016/j.apsusc.2013.09.002 ↗