CSC-YOLO: An Image Recognition Model for Surface Defect Detection of Copper Strip and Plates

doi:10.1007/s12204-024-2723-2

Abstract

Abstract: In order to meet the requirements of accurate identification of surface defects on copper strip in industrial production, a detection model of surface defects based on machine vision, CSC-YOLO, is proposed. The model uses YOLOv4-tiny as the benchmark network. First, K-means clustering is introduced into the benchmark network to obtain anchor frames that match the self-built dataset. Second, a cross-region fusion module is introduced in the backbone network to solve the difficult target recognition problem by fusing contextual semantic information. Third, the spatial pyramid pooling-efficient channel attention network (SPP-E) module is introduced in the path aggregation network (PANet) to enhance the extraction of features. Fourth, to prevent the loss of channel information, a lightweight attention mechanism is introduced to improve the performance of the network. Finally, the performance of the model is improved by adding adjustment factors to correct the loss function for the dimensional characteristics of the surface defects. CSC-YOLO was tested on the self-built dataset of surface defects in copper strip, and the experimental results showed that the mAP of the model can reach 93.58%, which is a 3.37% improvement compared with the benchmark network, and FPS, although decreasing compared with the benchmark network, reached 104. CSC-YOLO takes into account the real-time requirements of copper strip production. The comparison experiments with Faster RCNN, SSD300, YOLOv3, YOLOv4, Resnet50-YOLOv4, YOLOv5s, YOLOv7, and other algorithms show that the algorithm obtains a faster computation speed while maintaining a higher detection accuracy.

Key words: copper strip surface defect detection, K-means clustering, cross-region fusion module, spatial pyramid pooling-efficient channel attention network (SPP-E) module, YOLOv4-tiny

摘要： 为了满足工业生产中对铜板带产品表面缺陷进行准确识别的要求，提出了一种基于机器视觉的铜板带表面缺陷检测模型：CSC-YOLO。该模型以YOLOv4-tiny为基准网络，首先，在基准网络中引入K-means聚类，得到符合自建数据集的锚框；其次，在骨干网络中引入了跨特征的融合CRFM模块，通过融合上下文语义信息，解决困难目标识别问题；第三，在PANet网络中引入SPP-E模块加强特征提取；第四，为了防止通道信息的丢失，引入轻量化CBAM注意力机制提升网络的性能；最后，针对表面缺陷的尺寸特性，通过添加调节因子对损失函数进行修正，改善模型性能。CSC-YOLO在自建的铜板带表面缺陷数据集上进行了测试，实验结果表明：模型mAP可达到93.58%，与基准网络相比提升了3.37%，准确率与召回率均有提高，FPS虽然与基准网络相比有所下降，但也达到了104，CSC-YOLO兼顾了铜板带生产的实时性要求。在与Faster RCNN、SSD300、YOLOv3、YOLOv4、Resnet50-YOLOv4、YOLOv5s、YOLOv7等算法进行的对比实验表明，该算法在保持较高检测精度的同时，获得了较快的计算速度。

关键词: 铜板带表面缺陷检测，K-means聚类，跨特征融合模块，SPP-E模块，YOLOv4-tiny

CLC Number:

TP391

ZHANG Guo, CHEN Tao, WANG Jianping. CSC-YOLO: An Image Recognition Model for Surface Defect Detection of Copper Strip and Plates[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(5): 1037-1049.

References

[1] GONG S P. The status and development of copper strip products [J]. Shanghai Nonferrous Metals, 2011, 32(3): 140-143 (in Chinese).

[2] MENG F M. Development of copper strip defect online detection system based on ARM and DSP[D]. Hangzhou: China Jiliang University, 2019: 24-39 (in Chinese).

[3] LI J H. Research on key technology of surface defect detection in aluminum/copper strip[D]. Luoyang: Henan University of Science and Technology, 2019: 37-44 (in Chinese).

[4] ZHANG X W, GONG F, XU L Z. Inspection of surface defects in copper strip using multivariate statistical approach and SVM [J]. International Journal of Computer Applications in Technology, 2012, 43(1): 44-50.

[5] CHEN X C, LV J, FANG Y L, et al. Online detection of surface defects based on improved YOLOV3 [J]. Sensors, 2022, 22(3): 817.

[6] BAO Y Q, SONG K C, LIU J, et al. Triplet-graph reasoning network for few-shot metal generic surface defect segmentation [J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 5011111.

[7] LI J Y, SU Z F, GENG J H, et al. Real-time detection of steel strip surface defects based on improved YOLO detection network [J]. IFAC-PapersOnLine, 2018, 51(21): 76-81.

[8] KOU X P, LIU S J, CHENG K Q, et al. Development of a YOLO-V3-based model for detecting defects on steel strip surface [J]. Measurement, 2021, 182: 109454.

[9] WANG Z Y, ZHANG G, YANG Q, et al. Research on surface defect recognition of copper strip based on YOLOv4 [J]. Journal of Optoelectronics Laser, 2022, 33(2): 163-170 (in Chinese).

[10] XU Y H, WANG D C, LIU H M, et al. Intelligent recognition method for surface defects of cold rolling copper strip [J]. The Chinese Journal of Nonferrous Metals, 2022, 32(10): 2950-2964 (in Chinese).

[11] ZHENG X Q, CHEN J, WANG H C, et al. A deep learning-based approach for the automated surface inspection of copper clad laminate images [J]. Applied Intelligence, 2021, 51(3): 1262-1279.

[12] HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916.

[13] WANG Q L, WU B G, ZHU P F, et al. ECA-net: Efficient channel attention for deep convolutional neural networks [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 11531-11539.

[14] WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional block attention module [M]// Computer vision – ECCV 2018. Cham: Springer, 2018: 3-19.

[15] TAN M, LE Q. Efficientnetv2: Smaller models and faster training [C]// 38th International Conference on Machine Learning. PMLR, 2021: 10096-10106.

[16] 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. Las Vegas: IEEE, 2016: 770-778.

[17] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: Common objects in context[C]// Computer vision – ECCV 2014. Cham: Springer, 2014: 740-755.