LCD Mura defectimage segmentation based on improved Chan-Vese model

CHEN Ling-hai; YAO Jian-min; GUO Tai-liang

doi:10.3788/YJYXS20163106.0613

您当前的位置：

首页 >

文章列表页 >

LCD Mura defectimage segmentation based on improved Chan-Vese model

Display and Image | 更新时间：2020-08-12

- LCD Mura defectimage segmentation based on improved Chan-Vese model
- Chinese Journal of Liquid Crystals and Displays Vol. 31, Issue 6, Pages: 613-620(2016)
- 作者机构：
  
  福州大学物理与信息工程学院,福建福州,350002
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20163106.0613
  CLC： TN141.9
- Received：09 October 2015，
  
  Revised：21 December 2015，
  
  Published：05 June 2016
- 稿件说明：
移动端阅览
陈凌海, 姚剑敏, 郭太良. 基于改进Chan-Vese模型的液晶显示屏Mura缺陷分割[J]. 液晶与显示, 2016,31(6): 613-620

CHEN Ling-hai, YAO Jian-min, GUO Tai-liang. LCD Mura defectimage segmentation based on improved Chan-Vese model[J]. , 2016,31(6): 613-620
陈凌海, 姚剑敏, 郭太良. 基于改进Chan-Vese模型的液晶显示屏Mura缺陷分割[J]. 液晶与显示, 2016,31(6): 613-620 DOI： 10.3788/YJYXS20163106.0613.

CHEN Ling-hai, YAO Jian-min, GUO Tai-liang. LCD Mura defectimage segmentation based on improved Chan-Vese model[J]. , 2016,31(6): 613-620 DOI： 10.3788/YJYXS20163106.0613.

摘要

液晶显示屏Mura缺陷是一类较难检测的显示缺陷

它具有对比度低、背景亮度不均匀、边缘模糊等特点。针对传统Chan-Vese模型(C-V模型)对其分割时存在误分割及速度慢的问题

本文提出一种改进的C-V模型。首先

依据曲线演化理论

简化了传统C-V模型的图像数据力驱动项

这样减少了迭代过程中的计算量

提高了分割的速度。其次

为了平衡图像的亮度不均匀

在模型中引入一个新的能量项

该能量项与轮廓曲线内、外部之间的亮度差有关

提高了分割的准确性。最后

在算法的实现过程中引入迭代停止的判别式

通过设定分割的精度可以实现迭代的自动停止

并有利于正确地分割出目标。实验结果表明

本文提出的改进C-V模型能够准确分割背景不均匀的Mura缺陷

并且具有较快的速度。

Abstract

LCD Mura defect is difficult to detect. It has the features of low contrast

uneven brightness

blurry edge

and so on. The traditional Chan-Vese model (C-V model) cannot accurately segment the Mura defect and the segmentation speed is slow. In order to solve the problems

this paper presents an improved C-V model. First of all

according to the theory of curve evolution

the image data force in the traditional C-V model is simplified to reduce the iterative process of calculation and improve the segmentation speed. Secondly

in order to reduce the effect from non-uniformity brightness of image

the model is proved by adding a new energy term that related to the brightness difference between inside and outside area of the contour curve to improve the accuracy of the segmentation. Finally

the iterative stopping criterion is introduced in the implementation process of the algorithm

the setting of the segmentation accuracy can aid both in achieving the automatic iteration stop and segmenting the target correctly. Experimental results indicate that improved C-V model in this paper can accurately segment the background uneven Mura defect and it has a faster speed.

关键词

Keywords

references

李坤,李辉,刘云杰,等.LCD Mura缺陷的B样条曲面拟合背景抑制[J].光电工程,2014,41(2):33-39. LI K, LI H, LIU Y J, et al. Background suppression of LCD Mura defect using b-spline surface fitting[J]. Opto-Electronic Engineering, 2014, 41(2):33-39. (in Chinese)

刘毅,郑学仁.液晶屏显示缺陷自动检测系统的设计[J].微计算机信息,2008,24(19):250-251,297. LIUY, ZHENG X R. Design of LCD visual defect automated detecting system[J]. Microcomputer Information, 2008, 24(19):250-251, 297. (in Chinese)

LU C J, TSAI D M. Automatic defect inspection for LCDs using singular value decomposition[J]. International Journal of Production Research (S0020-7543), 2005, 43(21):4589-4607.

TSNENG Y H, TSAI D M. Defect detection of uneven brightness in low-contrast images using basis image representation[J]. Pattern Recognition, 2010, 43(3):1129-1141.

卢小鹏,李辉,刘云杰,等.基于Chan-Vese模型的TFT-LCD Mura缺陷快速分割算法[J].液晶与显示,2014,29(1):146-151. LUX P, LI H, LIU Y J, et al. Algorithm for fast TFT-LCD Mura defect image segmentation based on Chan-Vese model[J]. Chinese Journal of Liquid Crystals and Displays, 2014, 29(1):146-151. (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. BI X, DING H. Machine vision inspection method of Mura defect for TFT-LCD[J]. Journal of Mechanical Engineering, 2010, 46(12):13-19. (in Chinese)

东野长磊,郑永果,姜东焕,等.基于全局极小解Chan-Vese模型的SAR图像分割[J].计算机工程与设计,2012,33(11):4255-4258. DONGYEC L, ZHENG Y G, JIANG D H, et al. SAR image segmentation based on global minimization Chan-Vese model[J]. Computer Engineering and Design, 2012, 33(11):4255-4258. (in Chinese)

CHAN L A,VESE T F. Active contours without edges[J]. IEEE Transactions on Image Processing, 2001, 10(2):266-277.

龚劬,王迎龙,马家军.改进CV模型图像分割的Split-Bregman方法[J].计算机工程与应用,2015,51(6):171-175. GONGQ, WANG Y L, MA J J. Split-Bregman method for image segmentation of CV model[J]. Computer Engineering and Applications, 2015, 51(6):171-175. (in Chinese)

张开华,周文罡,张振,等.一种改进的C-V主动轮廓模型[J].光电工程,2008,35(12):112-116. ZHANGK H, ZHOU W G, ZHANG Z, et al. Improved C-V active contour model[J]. Opto-Electronic Engineering, 2008, 35(12):112-116. (in Chinese)

CHOPPD L. Computing minimal surfaces via level set curvature flow[J]. Journal of Computational Physics, 1993, 106(1):77-91.

WEICKERTJ, ROMENY B M T H, VIERGEVER M A. Efficient and reliable schemes for nonlinear diffusion filtering[J]. IEEE Transactions on Image Processing, 1998, 7(3):398-410.

KVHNE G, WEICKERT J, BEIER M, et al. Fast Implicit Active Contour Models[M]. Berlin Heidelberg:Springer-Verlag, 2002:133-140.

谢强军,侯迪波,黄平捷,等.一种改进的单参数水平集快速分割方法[J].光电子激光,2009,20(12):1671-1675. XIEQ J, HOU D B, HUANG P J, et al. An improved level set method for fast image segmentation based on single parameter[J]. Journal of OptoelectronicsLaser, 2009, 20(12):1671-1675. (in Chinese)

李俊,杨新,施鹏飞.基于Mumford-Shah模型的快速水平集图像分割方法[J].计算机学报,2002,25(11):1175-1183. LIJ, YANG X, SHI P F. A fast level set approach to image segmentation based on Mumford-shah model[J]. Chinese Journal of Computers, 2002, 25(11):1175-1183. (in Chinese)

朱晓舒,孙权森,夏德深.基于凸优化的自适应CV模型[J].计算机应用研究,2012,29(2):779-781. ZHUX S, SUN Q S, XIA D S. Adaptive CV model using convex optimization[J]. Application Research of Computers, 2012, 29(2):779-781. (in Chinese)

葛琦,韦志辉,张建伟,等.结合改进FCM算法的多相位CV模型[J].中国图象图形学报,2011,16(4):547-553. GEQ, WEI Z H, ZHANG J W, et al. Multiphase CV model integrated with improved FCM algorithm[J]. Journal of Image and Graphics, 2011, 16(4):547-553. (in Chinese)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Image segmentation based on improved Chan-Vese model

Algorithm for fast TFT-LCD Mura defect image segmentation based on Chan-Vese model

Related Author

YANG Ming-yu

LU Xiao-peng

LI Hui

LIU Yun-Jie

LIANG Ping

LI Kun

Related Institution

Key Laboratory of Airborne Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Science

School of Aeronautics and Astronautics, University of Electronic Science and Technology of China

Sichuan Entry-Exit Inspection and Quarantine Bureau

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰