钱基德,陈斌,钱基业,赵恒军,陈刚.基于机器视觉的液晶屏Mura缺陷检测方法[J].计算机科学,2018,45(6):296-300, 313
基于机器视觉的液晶屏Mura缺陷检测方法
Machine Vision Based Inspection Method of Mura Defect for LCD
投稿时间:2017-04-28  修订日期:2017-07-19
DOI:10.11896/j.issn.1002-137X.2018.06.052
中文关键词:  最大稳定极值,背景建模,背景差分,Mura缺陷,机器视觉
英文关键词:MSER,Background modeling,Background difference,Mura defect,Machine vision
基金项目:本文受四川省科技厅科技成果转化项目(2014CC0043),重庆市博士后科研项目特别资助
作者单位E-mail
钱基德 中国科学院成都计算机应用研究所 成都610041
中国科学院大学 北京100049 
 
陈斌 中科院广州电子技术研究所 广州 510070
中国科学院大学 北京100049 
chenbin306@sohu.com 
钱基业 国网重庆市电力公司电力科学研究院 重庆401123  
赵恒军 重庆文理学院 重庆402160  
陈刚 中国科学院成都计算机应用研究所 成都610041
中国科学院大学 北京100049 
 
摘要点击次数: 198
全文下载次数: 135
中文摘要:
      通过分析液晶屏中缺陷检测的必要性和人工检测的不足,研究一种基于机器视觉的液晶屏Mura缺陷在线检测系统。针对液晶屏中的Mura缺陷区域和周围背景对比度低、边缘模糊、形状各异、整体亮度不均等特点,建立模拟人工检测的成像系统。提出单帧图像背景建模和背景差分方法,该方法能有效解决液晶屏的亮度不均问题,同时增强Mura缺陷的特征信息。然后基于最大稳定极值区域(Maximally Stable Extremal Region,MSER),提出Mura缺陷自适应阈值缺陷分割方法,建立一个全自动缺陷在线检测的视觉系统。实验结果表明,所提检测算法能很好地解决液晶屏亮度不均的问题,准确地对Mura缺陷进行分割定位,算法的鲁棒性好。并且该系统人工干预少,效率高,能实现在线自动检测。
英文摘要:
      Analyzing the necessity of the defect detection and the disadvantage of the manual detection in the liquid crystal display(LCD),this paper studied a kind of online detection system for the Mura defect of LCD based on machine vision.There are some features of Mura such as the low contrast,the fuzzy edge,the irregular shapes,the uneven brightness and so on.The simulation computer vision system was built to imitate human detection.The single frame ima-ge background modeling and background subtraction method were proposed.The methods can effectively suppress the uneven brightness of the LCD,and enhance the features of Mura defect information.Then,based on the maximally stable extremal region(MSER),the Mura defect adaptive threshold segmentation method was proposed.The auto inspection machine vision system was set up by synthesizing the proposed methods.The experimental results show that the proposed detection algorithm can effectively suppress the uneven brightness of the LCD,and accurately segment the Mura defects with good robustness.The system has the advantages of less manual intervention,high accuracy and online automatic detection.
查看全文  查看/发表评论  下载PDF阅读器