Surface Defect Detection of Steel Based on Improved YOLOv5s
To address the issues of low accuracy and frequent occurrences of missed and false detections in steel surface defect detection, this paper proposes an algorithm named GSM-YOLO, which is based on YOLOv5s. Firstly, the Ghost Bottleneck module is introduced to improve the C3 module of the backbone network. The Ghost module is used to generate diverse feature maps to obtain more detailed information and increase the detection accuracy of the model. Secondly, a Spatial and Channel Reconstruction Convolution (SCConv) is incorporated to refine the feature information generated by the C3 module, making the output feature information more precise and consequently improving the detection accuracy of the algorithm. Finally, a Multi-dimensional Collaborative Attention (MCA) mechanism is added at the bottom of the SPPF module. Spatial and channel feature information from the three-branch structure of MCA is fused to enhance the model's attention for multi-scale target features, and then missed and false detections are reduced. The experimental results show that the proposed algorithm achieves a recall rate (R), precision (P), and mean average precision (mAP) which are 2.8%, 5.3% and 5.2% higher than those of the original network, respectively, on the NEU-DET dataset. This effectively enhances the ability to detect surface defects in steel materials.
References
- Li, J., Li, H., Hu, X. K., et al. Research Progress on Deep Learning-Based Surface Defect Detection Technology. Computer Integrated Manufacturing Systems, 2024, 30(3): 774-790. DOI:10.13196/j.cims.2023.IM28.
- Luo Q, Sun Y, Li P, et al. Generalized completed local binary patterns for time-efficient steel surface defect classification [J]. IEEE Transactions on Instrumentation and Measurement, 201 8, 68(3): 667-679.
- Kumar J, Srivastava S, Anand R S, et al. GLCM and ANN based approach for classification of radiographics weld images [C]. International Conference on Industrial and Information Systems, 201 8: 168-172.
- Cortes C. Support-Vector Networks [J]. Machine Learning, 1995.
- Rätsch G, Onoda T, Müller K R. Soft margins for AdaBoost [J]. Machine learning, 2001, 42: 287-320.
- Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks [J]. IEEE transactions on pattern analysis and machine intelligence, 2016, 39(6): 1137-1149.
- Xia K, Lv Z, Zhou C, et al. Mixed receptive fields augmented YOLO with multi-path spatial pyramid pooling for steel surface defect detection [J]. Sensors, 2023, 23(11): 5114.
- Wang L, Liu X, Ma J, et al. Real-time steel surface defect detection with improved multi-scale YOLO-v5 [J]. Processes, 2023, 11(5): 1357.
- Zhou, Y. L., Wu, X. C., Liu, W. G., et al. (2023). STCS-YOLO based algorithm for strip steel surface defect detection. China Metallurgy, 33(12), 128-138.
- Han K, Wang Y, Tian Q, et al. Ghostnet: More features from cheap operations [C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 1580-1589.
- Li J, Wen Y, He L. Scconv: Spatial and channel reconstruction convolution for feature redundancy [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 6153-6162.
- Yu Y, Zhang Y, Cheng Z, et al. MCA: Multidimensional collaborative attention in deep convolutional neural networks for image recognition [J]. Engineering Applications of Artificial Intelligence, 2023, 126: 107079.
- Xin H, Song J. YOLOv5-ACCOF Steel Surface Defect Detection Algorithm [J]. IEEE Access, 2024
- Fan J, Wang M, Li B, et al. ACD‐YOLO: Improved YOLOv5‐based method for steel surface defects detection [J]. IET Image Processing, 2024, 18(3): 761-771.
- Zhang, S. Q., Shi, W. Y., Zhang, S. W., et al. (2023). Steel surface defect detection based on improved YOLOv5 algorithm. Science Technology and Engineering, 23(35), 15148-15157.