液晶与显示2024，Vol.39Issue(6)：790-800,11.DOI:10.37188/CJLCD.2023-0206
基于YOLOv5的液晶屏微弱特征缺陷检测算法
Weak feature defect detection method for LCD screens based on YOLOv5
摘要
Abstract
To address the problem of low detection accuracy of weak feature defects in LCD display defects caused by multiple convolution and background texture assimilation,an improved model YOLO-Mura for LCD weak feature defect detection based on YOLOv5 is proposed.Firstly,Involution operator is introduced in the backbone network to expand perceptual field,enhance the information of weak feature defects in spatial range,and reduce model FLOPs.Secondly,the CARAFE upsampling operator is used to optimize the upsampling method and enhance the ability to focus on weak feature defects.Then,in the neck network,the feature extraction ability of the network under strong background interference is enhanced by embedding the BiFormer attention module.Finally,the BiFPN weighted bidirectional pyramid structure is adopted to improve the feature fusion utilization at different levels.Experimental results on the homemade LCD Mura defect dataset show that the accuracy,recall,and mAP@0.5 of YOLO-Mura model are improved by 2.2%,6.6%,and 2.7%,respectively,and the model computation is reduced by 66.5%.In comparison with the mainstream target detection algorithms,the results show that the final improved model in this paper has better detection performance for Mura defects with weak features of LCDs.关键词
液晶屏/Mura缺陷/YOLOv5算法/微弱特征检测Key words
LCD screen/Mura defects/YOLOv5 algorithm/weak feature detection分类
信息技术与安全科学引用本文复制引用
林峰,石艳,陈顺龙,廖映华,赵练,赵黎,周泽民..基于YOLOv5的液晶屏微弱特征缺陷检测算法[J].液晶与显示,2024,39(6):790-800,11.基金项目
宜宾市科技厅重点研发项目(No.2021GY0011) （No.2021GY0011）
宜宾市三江新区揭榜挂帅项目(No.2022JBGS001) （No.2022JBGS001）
四川轻化工大学研究生创新基金(No.Y2022056)Supported by R&D Project of Yibin Science and Technology Department(No.2021GY0011) （No.Y2022056）
Yibin Sanjiang New Area Unveiling Hanging Project(No.2022JBGS001) （No.2022JBGS001）
Sichuan University of Light Industry Graduate Innovation Fund(No.Y2022056) （No.Y2022056）
