首页 > 论文 > 液晶与显示 > 33卷 > 6期(pp:475-482)

基于自适应局部增强的手机TFT-LCD屏Mura缺陷自动检测

Automatic detection of Mura defect in TFT-LCD mobile screen based on adaptive local enhancement

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对手机屏幕图像整体亮度不均以及Mura缺陷对比度低等特点,提出一种基于自适应局部增强的Mura缺陷自动在线检测方法。首先对CCD相机采集的手机屏幕原始图像进行感兴趣区域提取、几何校正、滤波等预处理,获取图像中的屏幕区域,然后将屏幕区域划分为多个不重叠的像素块,并根据每个像素块的灰度分布特征,采用自适应局部增强算法自动识别并定位图像中的Mura区域,最后考虑到Mura缺陷大小的不确定,提出采用多层级分块的方式对屏幕区域进行检测,提高算法鲁棒性。实验结果表明,相较现有多种屏幕缺陷自动检测算法,本文方法能更准确有效地识别手机屏幕中的Mura缺陷,且覆盖率和误检率分别为91.17%和5.84%。

Abstract

Aiming at the characteristics of mobile screen image, such as non-uniform luminance and low contrast of Mura defect, an automatic on-line detection method for Mura defect based on adaptive local enhancement is proposed in this paper. First, for the original mobile screen image captured by CCD camera, preprocessing steps including region of interest extraction, geometric correction and filtering are applied to extract the screen region from the original image. Then, the screen region is divided into multiple non-overlapping pixel blocks, and the Mura regions in each block are recognized and located by adaptive local enhancement according to the intensity distribution of each block. Finally, to increase the robustness of the algorithm, a multi-level partitioning scheme is proposed in this paper to detect the Mura defects with different sizes. Experimental results show that, compared to many automatic screen defect detection methods, the proposed method can detect the Mura defects from mobile screen more accurately and effectively, and the percentages of overlapping and detection error are 91.17% and 5.84%, respectively.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/yjyxs20183306.0475

所属栏目:材料与器件

基金项目:国家自然科学基金资助项目(No.61702179);湖南省自然科学基金资助项目(No.2017JJ3091, No. 2016JJ2057);湖南省教育厅资助科研项目(No.17C0643, No.15C0546);湖南科技大学校级科研项目(No.E51754);中国博士后科学基金资助项目(No.2018M632994);中南大学博士后基金(No.202594).

收稿日期:2018-01-18

修改稿日期:2018-04-02

网络出版日期:--

作者单位    点击查看

廖 苗:湖南科技大学 计算机科学与工程学院,湖南 湘潭411100
刘毅志:湖南科技大学 计算机科学与工程学院,湖南 湘潭411100
欧阳军林:湖南科技大学 计算机科学与工程学院,湖南 湘潭411100
余建勇:湖南科技大学 计算机科学与工程学院,湖南 湘潭411100
肖文辉:湖南科技大学 计算机科学与工程学院,湖南 湘潭411100
彭 理:湖南科技大学 计算机科学与工程学院,湖南 湘潭411100

联系人作者:廖苗(liaomiaohi@163.com)

备注:廖苗(1988-),女,湖南常德人,博士,讲师,主要研究方向:数字图像处理、模式识别与人工智能。

【1】高如新,任晓朵,吴献,等.基于图像处理的手机屏幕缺陷检测系统研究[J].测控技术,2017,36(4):26-30.
GAO R X, REN X D, WU X, et al. Research on mobile phone screen defect detection system based on image processing [J]. Measurement & Control Technology, 2017, 36(4): 26-30. (in Chinese)

【2】CEN Y G, ZHAO R Z, CEN L H, et al. Defect inspection for TFT-LCD images based on the low-rank matrix reconstruction[J]. Neurocomputing, 2015, 149: 1206-1215.

【3】刘波,李新华,钱翔,等.手机屏幕图像缺陷的实时检测[J].计算机工程与应用,2010,46(28):77-79.
LIU B, LI X H, QIAN X, et al. Real time detection of image defect for phone LCD screen [J]. Computer Engineering and Applications, 2010, 46(28): 77-79. (in Chinese)

【4】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.

【5】JIANC X, CAO J, AO Y H. Automatic surface defect detection for mobile phone screen glass based on machine vision [J]. Applied Soft Computing, 2017, 52: 348-358.

【6】温招洋,周亚丽,张奇志.基于DCT和Otsu的LCD缺陷检测算法[J].北京信息科技大学学报:自然科学版,2017,32(2):50-54.
WEN Z Y, ZHOU Y L, ZHANG Q Z. Defect detection algorithm of LCD based on DCT and Otsu [J]. Journal of Beijing Information Science & Technology University, 2017, 32(2): 50-54. (in Chinese)

【7】GUE, PARK K H, LEE J H, et al. TFT-LCD defect detection based on histogram distribution modeling [J]. Journal of Korea Multimedia Society, 2015, 18(12): 1519-1527.

【8】GU E, PARK K H. Defect Detection algorithm of TFT-LCD polarizing film using the probability density function based on cluster characteristic [J]. Journal of Korea Multimedia Society, 2016, 19(3): 633-641.

【9】WANG X, DONG R, LI B. TFT-LCD Mura defect detection based on ICA and multi-channels fusion [C]//Proceedings of 3rd International Conference on Information Science and Control Engineering. Beijing, China: IEEE, 2016: 687-691.

【10】许祖鑫,毕明德,孙志刚.基于数学形态学的手机屏缺陷检测算法设计[J].电气自动化,2013,35(3):99-101,105.
XU Z X, BI M D, SUN Z G. Design of defect inspection algorithm for mobile screen based on mathematical morphology [J]. Electrical Automation, 2013, 35(3): 99-101, 105. (in Chinese)

【11】刘毅,郑学仁,王亚南,等.MATLAB在TFT-LCD屏显示MURA缺陷检测的应用[J].液晶与显示,2007,22(6):731-736.
LIU Y, ZHENG X R, WANG Y N, et al. Application of MATLAB in TFT-LCD’s MURA defect detection [J]. Chinese Journal of Liquid Crystals and Displays, 2007, 22(6): 731-736. (in Chinese)

【12】OTSU N. A threshold selection method from gray-level histograms [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.

引用该论文

LIAO Miao,LIU Yi-zhi,OU YANG Jun-lin,YU jian-yong,XIAO wen-hui,PENG Li. Automatic detection of Mura defect in TFT-LCD mobile screen based on adaptive local enhancement[J]. Chinese Journal of Liquid Crystals and Displays, 2018, 33(6): 475-482

廖 苗,刘毅志,欧阳军林,余建勇,肖文辉,彭 理. 基于自适应局部增强的手机TFT-LCD屏Mura缺陷自动检测[J]. 液晶与显示, 2018, 33(6): 475-482

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF