基于YOLO v3的贴装元器件检测技术  

Mounted component inspection technology based on YOLO v3

作　　者：窦子豪 刘新妹[1] 殷俊龄[1] 曹富强 Dou Zihao;Liu Xinmei;Yin Junling;Cao Fuqiang(State Key Laboratory of Electronic Testing Technology,North University of China,Taiyuan 030051,China;Department of Information and Communication Engineering,North University of China,Taiyuan 030051,China)

机构地区：[1]中北大学电子测试技术国家重点实验室,太原030051 [2]中北大学信息与通信工程学院,太原030051

出　　处：《电子测量技术》2021年第13期127-131,共5页Electronic Measurement Technology

基　　金：山西省回国留学人员科研项目(2017-090);山西省重点研发项目(201903D121058)资助。

摘　　要：印制电路板表面贴装元器件的识别分类技术在现代化电子产业生产过程中起重要作用,以PCB表面的贴装电阻、贴装电容、芯片等为目标,提出了一种基于YOLO v3的目标检测方法。首先利用工业相机搭配光学镜头构建贴装元器件数据集,其次重新设计了YOLO v3的特征金字塔结构FPN,接着采用K-means方法对贴装元器件数据集进行聚类改进,得到Mouted anchor及对应参数。最后使用Mounted anchor和网络结构对改进后的YOLO v3重训练,并与原网络对比实验,检验了贴装元器件的识别分类效果。实验结果表明,改进后的YOLO v3贴装元器件识别分类技术平均精确率较原网络提高9%,召回率小幅提高。The identification and classification technology of printed circuit board surface mount components plays an important role in the production process of modern electronics industry. A target detection method based on YOLO v3. First, an industrial camera is used with an optical lens to construct a data set of mounted components, and secondly, the feature pyramid structure FPN of YOLO v3 is redesigned, and then the K-means method is used to improve the clustering of the mounted component data set. Get the Mouted anchor and corresponding parameters. Finally, use Mounted anchor and network structure to retrain the improved YOLO v3, and compare experiments with the original network to verify the recognition and classification effect of the mounted components. The experimental results show that the improved YOLO v3 mounted component recognition and classification technology has an average accuracy rate of 9% higher than that of the original network, and a slight increase in the recall rate.

关 键 词：图像处理 YOLO v3 特征金字塔 聚类算法 无损检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]