电子测量与仪器学报

杨永跃,夏远超.PCB 缺陷检测深度学习算法的精度改进[J].电子测量与仪器学报,2023,37(5):11-19

PCB 缺陷检测深度学习算法的精度改进

Accuracy improvement of deep learning algorithm for PCB defect detection

DOI：

英文关键词:PCB defect detection object detection deep learning YOLO

基金项目:国家科技部重大科学仪器专项项目(2013YQ220749)资助

作者	单位
杨永跃	1.合肥工业大学仪器科学与光电工程学院
夏远超	1.合肥工业大学仪器科学与光电工程学院

Author	Institution
Yang Yongyue	1.School of Instrument Science and Opto-Electronics Engineering, Hefei University of Technology
Xia Yuanchao	1.School of Instrument Science and Opto-Electronics Engineering, Hefei University of Technology

摘要点击次数: 221

全文下载次数: 516

中文摘要:

本文以 YOLOv5 目标检测算法为基础算法,针对 PCB 缺陷检测进行了提高精度的改进。首先通过实验选取了合适的数据增强方法。针对 PCB 缺陷尺寸小的问题,在原有的 3 个检测头基础上增加了 P2 检测头。设计全新的 PANet 多特征融合结构,实现高效的双向跨尺度连接和加权特征层融合。针对 PCB 背景复杂的问题,引入了 CBAM 注意力模块以增强图像信息。引入了 Transformer 模块来增强算法,以提高捕捉不同位置的 PCB 缺陷信息的能力。最终通过这些改进,在检测速度 FPS 仅下降 7. 2 的情况下,检测算法的 mAP 精度提高了 11. 3%。

英文摘要:

In this paper, the YOLOv5 target detection algorithm was used as the base algorithm to improve accuracy for PCB defect detection. Firstly, an appropriate data augmentation method is selected through experiments. For the problem of small PCB defect size, the P2 detection head was added to the original three detection heads. A new PANet multi-feature fusion structure was designed to realize efficient two-way cross-scale connection and weighted feature layer fusion. For the problem of the complex PCB background, the CBAM attention module is introduced to enhance image information, the Transformer module is introduced to enhance the algorithm’s ability to capture PCB defect information at different locations. Finally, through these improvements, the mAP accuracy of the algorithm increased by 11. 3% while the FPS droped by only 7. 2.

查看全文查看/发表评论下载PDF阅读器