@article{LIU2026, 
author = {Chunjuan LIU and Mingxuan ZHANG and Haowen YAN and Xiaosuo WU and Yixiang WANG},
title = {CSYOLO: a YOLOv8-based PCB defect detection model integrating composite backbone networks and dynamic snake convolution},
year = {2026},
journal = {Journal of Measurement Science and Instrumentation},
volume = {17},
number = {1},
pages = {151-161},
keywords = {printed circuit board (PCB), deep learning, defect detection, YOLOv8, multi-scale feature fusion, loss function},
url = {https://www.sciopen.com/article/10.62756/jmsi.1674-8042.2026013},
doi = {10.62756/jmsi.1674-8042.2026013},
abstract = {An improved CSYOLOv8 model based on YOLOv8 model is developed specifically for identifying defects in printed circuit board (PCB). Firstly, a composite backbone network is designed to carry out additional feature extraction, which enriches the expression ability of features and enhances the detection accuracy of the model. Secondly, a YOLO-FPN (Feature pyramid network) structure is designed to supplant the original neck network, which enhances the feature fusion ability of the model and improves the detection accuracy of small target objects. Furthermore, to enhance the model’s capability to extract tubular features, dynamic snake convolution is implemented. Finally, MPDIoU loss function is employed to enhance both the convergence rate and the precision of the model. Experiments show that the mAP of the improved model on the PCB defect dataset reaches 96.6%, which is 4.5% higher than that of the YOLOv8 model, and the number of parameters is only 3256862, and the average detection speed is 51.8 frames per second, which meets the requirements of detection accuracy and efficiency.}
}