计算机科学 ›› 2018, Vol. 45 ›› Issue (6): 296-300.doi: 10.11896/j.issn.1002-137X.2018.06.052

• 图形图像与模式识别 • 上一篇    下一篇

基于机器视觉的液晶屏Mura缺陷检测方法

钱基德1,5, 陈斌2,5, 钱基业3, 赵恒军4, 陈刚1,5   

  1. 中国科学院成都计算机应用研究所 成都6100411;
    中科院广州电子技术研究所 广州 5100702;
    国网重庆市电力公司电力科学研究院 重庆4011233;
    重庆文理学院 重庆4021604;
    中国科学院大学 北京1000495
  • 收稿日期:2017-04-28 出版日期:2018-06-15 发布日期:2018-07-24
  • 作者简介:钱基德(1988-),男,博士生,主要研究方向为机器学习与计算机视觉;陈 斌(1970-),男,研究员,博士生导师,主要研究方向为实时工业图像分析、字符识别和智能视觉控制,E-mail:chenbin306@sohu.com(通信作者);钱基业(1982-),男,博士,主要研究方向为机器视觉、机器学习和传感器信号处理;赵恒军(1982-),男,副教授,主要研究方向为模式识别、图像分析与处理;陈 刚(1984-),男,博士生,主要研究方向为机器学习与图像处理
  • 基金资助:
    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(Xm2016060),重庆市教育委员会科学技术研究项目(KJ1401127)资助

Machine Vision Based Inspection Method of Mura Defect for LCD

QIAN Ji-de1,5, CHEN Bin2,5, QIAN Ji-ye3, ZHAO Heng-jun4, CHEN Gang1,5   

  1. Chengdu Institute of Computer Application,Chinese Academy of Sciences,Chengdu 610041,China1;
    Guangzhou Institute of Electronic Technology,Chinese Academy of Sciences,Guangzhou 510070,China2;
    State Grid Chongqing Electric Power Co.Electric Power Research Institute,Chongqing 401123,China3;
    Chongqing University of Arts and Sciences,Chongqing 402160,China4;
    University of Chinese Academy Sciences,Beijing 100049,China5
  • Received:2017-04-28 Online:2018-06-15 Published:2018-07-24

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。

关键词: Mura缺陷, 背景差分, 背景建模, 机器视觉, 最大稳定极值

Abstract: 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.

Key words: Background difference, Background modeling, Machine vision, MSER, Mura defect

中图分类号: 

  • TP274
[1]CHOI Y S,YUN J U,PARK S E.Flat panel display glass:Current status and future[J].Journal of Non-Crystalline Solids,2016,431:2-7.
[2]BI X,DING H.Machine Vision Inspection Method of Mura Defect for TFT-LCD[J].Chinese Journal of Mechanical Enginee-ring,2010,46(12):13-19.(in Chinese)
毕昕,丁汉.TFT-LCD Mura缺陷机器视觉检测方法[J].机械工程学报,2010,46(12):13-19.
[3]HE Z,SUN L.Surface defect detection method for glass substrate using improved Otsu segmentation[J].Applied Optics,2015,54(33):9823.
[4]TSAI D M,TSENG Y H,CHIU W Y.Surface defect detection in low-contrast images using basis image representation[C]//IAPR International Conference on Machine Vision Applications.2015:186-189.
[5]FAN S K S,CHUANG Y C.Automatic detection of Mura defect in TFT-LCD based on regression diagnostics[J].Pattern Recognition Letters,2010,31(15):2397-2404.
[6]YANG Y B,LI N,ZHANG Y.Automatic TFT-LCD mura detection based on image reconstruction and processing[C]//IEEE Third International Conference on Consumer Electronics-Berlin.2013:240-244.
[7]JIANG B C,WANG C C,LIU H C.Liquid crystal display surface uniformity defect inspection using analysis of variance and exponentially weighted moving average techniques[J].International Journal of Production Research,2005,43(1):67-80.
[8]FORSSEN P E,LOWE D G.Shape Descriptors for Maximally Stable Extremal Regions[C]//IEEE International Conference on Computer Vision.2007:1-8.
[9]YOSHINAGA S,SHIMADA A,NAGAHARA H,et al.Object detection based on spatiotemporal background models[J].Computer Vision and Image Understanding,2014,122(5):84-91.
[10]MOSHE Y,HELOR H,HELOR Y.Foreground detection using spatiotemporal projection kernels[C]//IEEE Conference on Computer Vision and Pattern Recognition.2012:3210-3217.
[11]Horprasert T,Harwood D,Davis L S.A statistical approach for real-time robust background subtraction and shadow detection[C]//IEEE International Conference on Computer Vision.1999:1-19.
[12]LIU Y J,ZHI M.A two-layer background modeling method based on codebook and running average[J].Computer Enginee-ring and Science,2016,38(6):1220-1224.(in Chinese)
刘妍江,智敏.基于码本和运行期均值法的双层背景建模方法[J].计算机工程与科学,2016,38(6):1220-1224.
[13]STAUFFER C,GRIMSON W E L.Adaptive Background Mixture Models for Real-Time Tracking[C]//IEEE International Conference on Computer Vision and Pattern Recognition.1999:246-252.
[14]WANG S F,YAN J H,WANG Z G.Improved moving object detection algorithm based on local united feature[J].Chinese Journal of Scientific Instrument,2015,36(10):2241-2248.(in Chinese)
王顺飞,闫钧华,王志刚.改进的基于局部联合特征的运动目标检测方法[J].仪器仪表学报,2015,36(10):2241-2248.
[15]MATAS J,CHUM O,URBAN M,et al.Robust wide-baseline stereo from maximally stable extremal regions[J].Image and Vision Computing,2004,22(10):761-767.
[16]DING W R,KANG C B,LI H G,et al.Building areas extraction basing on MSER in unmanned aerial vehicle image[J].Journal of Beijing University of Aeronautics and Astronautics,2015,41(3):383-390.(in Chinese)
丁文锐,康传波,李红光,等.基于MSER的无人机图像建筑区域提取[J].北京航空航天大学学报,2015,41(3):383-390.
[17]NISTÉR D,STEWÉNIUS H.Linear Time Maximally Stable Extremal Regions[C]//European Conference on Computer Vision.2008:183-196.
[18]REN S G,MA C,XU H L.Improved Skeleton Extraction Algorithm Based Active Contour Model Research[J].Computer Scien-ce,2013,40(7):289-292.(in Chinese)
任守纲,马超,徐焕良.基于改进主动轮廓模型的图像分割方法研究[J].计算机科学,2013,40(7):289-292.
[19]SHI Y G,TAN J S,LIU Z W.Renal Cortex Segmentation Using Graph Cuts and Level Set[J].Computer Science,2016,43(7):290-293.(in Chinese)
时永刚,谭继双,刘志文.基于图割和水平集的肾脏医学图像分割[J].计算机科学,2016,43(7):290-293.
[1] 王栋, 周大可, 黄有达, 杨欣.
基于多尺度多粒度特征的行人重识别
Multi-scale Multi-granularity Feature for Pedestrian Re-identification
计算机科学, 2021, 48(7): 238-244. https://doi.org/10.11896/jsjkx.200600043
[2] 王恰, 戚湧.
基于帧间差分和统计直方图的交通视频背景建模方法
Method for Traffic Video Background Modeling Based on Inter-frame Difference and Statistical Histogram
计算机科学, 2020, 47(10): 174-179. https://doi.org/10.11896/jsjkx.190800014
[3] 韩克堃, 胡桂川, 任静, 何鸿宇, 刘佳音.
图像处理在风电叶片法兰端面特征尺寸检测中的应用
Application of Image Processing in Feature Size Detection of Wind Turbine Blade’s Flange Face
计算机科学, 2019, 46(6A): 562-565.
[4] 李堃, 黎向锋.
基于日间行车的灯语识别技术
Lamp Language Recognition Technology Based on Daytime Driving
计算机科学, 2019, 46(11A): 277-282.
[5] 韩绍超,徐遵义,尹中川,王俊雪.
指针式仪表自动读数识别技术的研究现状与发展
Research Review and Development for Automatic Reading Recognition Technology of Pointer Instruments
计算机科学, 2018, 45(6A): 54-57.
[6] 张文勇, 陈乐柱.
基于LabVIEW机器视觉的餐具分拣系统
Tableware Sorting System Based on LabVIEW Machine Vision
计算机科学, 2018, 45(6A): 595-597.
[7] 高飞,丰敏强,汪敏倩,卢书芳,肖刚.
基于热点区域定义的人数统计方法研究
Research on People Counting Based on Hot Area
计算机科学, 2017, 44(Z6): 173-178. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.040
[8] 朱航江,朱帆,潘振福,朱永利.
运动状态与尺度估计的核相关目标跟踪方法
Visual Object Tracking Method with Motion Estimation and Scale Estimation
计算机科学, 2017, 44(Z11): 193-198. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.040
[9] 张文雅,徐华中,罗杰.
基于ViBe的复杂背景下的运动目标检测
Moving Objects Detection under Complex Background Based on ViBe
计算机科学, 2017, 44(9): 304-307. https://doi.org/10.11896/j.issn.1002-137X.2017.09.057
[10] 汪荣琪,郑林,王标.
基于改进的PBAS算法的前景目标检测
Foreground Object Detection Based on Improved PBAS
计算机科学, 2017, 44(5): 294-298. https://doi.org/10.11896/j.issn.1002-137X.2017.05.054
[11] 宣寒宇,刘宏哲,袁家政,李青,牛小宁.
一种鲁棒性的多车道线检测算法
Robust Multi-lane Detection Algorithm
计算机科学, 2017, 44(11): 305-313. https://doi.org/10.11896/j.issn.1002-137X.2017.11.047
[12] 李飞,张小洪,赵晨丘,鄢萌.
自适应的SILTP算法在运动车辆检测中的研究
Vehicle Detection Research Based on Adaptive SILTP Algorithm
计算机科学, 2016, 43(6): 294-297. https://doi.org/10.11896/j.issn.1002-137X.2016.06.058
[13] 蒋泳森,肖泉,王守觉.
基于矢量方向特征的非参数动态背景建模
Non-parametric Dynamic Background Modeling Based on Direction Feature of Vector
计算机科学, 2016, 43(3): 291-295. https://doi.org/10.11896/j.issn.1002-137X.2016.03.054
[14] 田合雷,丁胜,于长伟,周立.
基于目标检测及跟踪的视频摘要技术研究
Research of Video Abstraction Based on Object Detection and Tracking
计算机科学, 2016, 43(11): 297-299. https://doi.org/10.11896/j.issn.1002-137X.2016.11.057
[15] 徐振驰,纪磊,刘晓荣,周晓佳.
基于显著性特征的食用菌中杂质检测
Recognition of Impurities Based on their Distinguishing Feature in Mushrooms
计算机科学, 2015, 42(Z11): 203-205.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!