SPDConv structure diagram. حسب Jia Li (160557)

"…To address this problem, this paper proposes a YOLOv8-based insulator defect detection algorithm, YOLOv8-SSF. Firstly, SimAM (parameter-free attention mechanism) is included in the algorithm’s backbone network, which improves the ability to focus on critical features while maintaining a lightweight model. …"

Dataset. حسب Xuanyi Zhao (5896112)

"…<div><p>In recent years, the demand for efficient and accurate defect detection algorithms in industrial production has been increasing. …"

Loss curve comparison diagram. حسب Jia Li (160557)

"…To address this problem, this paper proposes a YOLOv8-based insulator defect detection algorithm, YOLOv8-SSF. Firstly, SimAM (parameter-free attention mechanism) is included in the algorithm’s backbone network, which improves the ability to focus on critical features while maintaining a lightweight model. …"

Visualisation and analysis of test results. حسب Jia Li (160557)

"…To address this problem, this paper proposes a YOLOv8-based insulator defect detection algorithm, YOLOv8-SSF. Firstly, SimAM (parameter-free attention mechanism) is included in the algorithm’s backbone network, which improves the ability to focus on critical features while maintaining a lightweight model. …"

Performance of different algorithms. حسب Shiwei Yu (6060308)

"…This paper proposes a lightweight PCB defect detection algorithm based on YOLO. To address the problem of large numbers of parameters and calculations, GhostNet are used in Backbone to keep the model lightweight. …"

SCUNet structured flowchart. حسب Xuanyi Zhao (5896112)

"…<div><p>In recent years, the demand for efficient and accurate defect detection algorithms in industrial production has been increasing. …"

SCUNet Network structure diagram. حسب Xuanyi Zhao (5896112)

"…<div><p>In recent years, the demand for efficient and accurate defect detection algorithms in industrial production has been increasing. …"

Comparison of mAP@0.5 and mAP@0.5:0.95 curves. حسب Jia Li (160557)

"…To address this problem, this paper proposes a YOLOv8-based insulator defect detection algorithm, YOLOv8-SSF. Firstly, SimAM (parameter-free attention mechanism) is included in the algorithm’s backbone network, which improves the ability to focus on critical features while maintaining a lightweight model. …"

Overall system framework. حسب Xuanyi Zhao (5896112)

"…<div><p>In recent years, the demand for efficient and accurate defect detection algorithms in industrial production has been increasing. …"

Experimental parameter settings. حسب Shiwei Yu (6060308)

"…This paper proposes a lightweight PCB defect detection algorithm based on YOLO. To address the problem of large numbers of parameters and calculations, GhostNet are used in Backbone to keep the model lightweight. …"

Comparison table of filter algorithm parameters. حسب Xuanyi Zhao (5896112)

"…<div><p>In recent years, the demand for efficient and accurate defect detection algorithms in industrial production has been increasing. …"

Detection results for the migrated application. حسب Xuanyi Zhao (5896112)

"…<div><p>In recent years, the demand for efficient and accurate defect detection algorithms in industrial production has been increasing. …"

Revised yolov8 training process. حسب Xuanyi Zhao (5896112)

"…<div><p>In recent years, the demand for efficient and accurate defect detection algorithms in industrial production has been increasing. …"

YOLOv8 improved network structure diagram. حسب Xuanyi Zhao (5896112)

"…<div><p>In recent years, the demand for efficient and accurate defect detection algorithms in industrial production has been increasing. …"

Experimental environment configuration. حسب Shiwei Yu (6060308)

"…This paper proposes a lightweight PCB defect detection algorithm based on YOLO. To address the problem of large numbers of parameters and calculations, GhostNet are used in Backbone to keep the model lightweight. …"

Industrial smoke vapor. حسب Xuanyi Zhao (5896112)

"…<div><p>In recent years, the demand for efficient and accurate defect detection algorithms in industrial production has been increasing. …"

The network structure of our model. حسب Shiwei Yu (6060308)

"…This paper proposes a lightweight PCB defect detection algorithm based on YOLO. To address the problem of large numbers of parameters and calculations, GhostNet are used in Backbone to keep the model lightweight. …"

The structural layout of the Ghost module. حسب Shiwei Yu (6060308)

"…This paper proposes a lightweight PCB defect detection algorithm based on YOLO. To address the problem of large numbers of parameters and calculations, GhostNet are used in Backbone to keep the model lightweight. …"

The CBS structure improvement based on DSConv. حسب Shiwei Yu (6060308)

"…This paper proposes a lightweight PCB defect detection algorithm based on YOLO. To address the problem of large numbers of parameters and calculations, GhostNet are used in Backbone to keep the model lightweight. …"

The improved C3STR structure. حسب Shiwei Yu (6060308)

"…This paper proposes a lightweight PCB defect detection algorithm based on YOLO. To address the problem of large numbers of parameters and calculations, GhostNet are used in Backbone to keep the model lightweight. …"