TFT array defect detection based on AttentionGAN and morphological reconstruction

Wei-wei CHEN; Qun YAN; Jian-min YAO

doi:10.37188/YJYXS20203512.1270

您当前的位置：

首页 >

文章列表页 >

TFT array defect detection based on AttentionGAN and morphological reconstruction

Device Preparation & Detection | 更新时间：2020-12-04

- TFT array defect detection based on AttentionGAN and morphological reconstruction
- Chinese Journal of Liquid Crystals and Displays Vol. 35, Issue 12, Pages: 1270-1277(2020)
- 作者机构：
  
  1.福州大学物理与信息工程学院, 福建福州 350108
  2.晋江市博感电子科技有限公司, 福建晋江 362200
- 作者简介：
- 基金信息：
- DOI：10.37188/YJYXS20203512.1270
  CLC： TP394.1;TH691.9
- Received：10 July 2020，
  
  Revised：17 August 2020，
  
  Accepted：2020-8-17，
  
  Published：2020-12
- 稿件说明：
移动端阅览
Wei-wei CHEN, Qun YAN, Jian-min YAO. TFT array defect detection based on AttentionGAN and morphological reconstruction[J]. Chinese journal of liquid crystals and displays, 2020, 35(12): 1270-1277.
DOI：

Wei-wei CHEN, Qun YAN, Jian-min YAO. TFT array defect detection based on AttentionGAN and morphological reconstruction[J]. Chinese journal of liquid crystals and displays, 2020, 35(12): 1270-1277. DOI： 10.37188/YJYXS20203512.1270.

摘要

缺陷检测在TFT阵列工艺的良率提高中起着重要作用，传统的人工识别效率低，新兴的目标检测卷积神经网络在缺陷标注上需要耗费大量人力。为了实现TFT阵列缺陷自动检测的同时尽可能地减少人工成本，提出了一种基于生成对抗网络和形态学重建的TFT阵列缺陷检测方法，该方法中用于训练网络的数据集无需人工标注，解决了人工标注成本大的问题。该方法首先通过AttentionGAN网络得到TFT阵列的显著性图，接着选定显著性图中显著性最低的像素为种子点，得到缺陷标记图像与缺陷掩膜图像，进而进行二值形态学重建的区域生长，最后得到缺陷的检测。该方法对于TFT阵列缺陷的二分类能达到F1分数为0.94的结果，为TFT阵列的自动化缺陷检测提出了一种新思路。

Abstract

Defect detection plays an important role in yield improvement for TFT array process. Traditional manual recognition is inefficient

while the emerging convolutional neural network for target detection needs a lot of manpower in defect labeling. In order to realize the automatic detection of TFT array defects while reducing labor costs as much as possible

a TFT array defect detection method based on Generative Adversarial Networks and morphological reconstruction is proposed. In this method

the dataset used to train the network does not need to be manually labeled

which solves the problem of high manual labeling costs. This method first obtains the attention mask of the TFT array through the AttentionGAN network

secondly

selects the least significant pixel in the attention mask as the seed point

obtains the defect mark image and the defect mask image

and then performs the region growth for binary morphological reconstruction

finally get the bounding box of defect. This method can achieve an F1 score of 0.94 for the two-class classification of TFT array defects

which proposes a new idea for automatic defect detection of TFT array.

关键词

Keywords

references

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 . 液晶与显示 , 2016 . 31 ( 6 ): 613 - 620 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1705661&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1705661&Fpath=&index=-1&l=zh .

L H CHEN , J M YAO , T L GUO . LCD Mura defectimage segmentation based on improved Chan-Vese model . Chinese Journal of Liquid Crystals and Displays , 2016 . 31 ( 6 ): 613 - 620 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1705661&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1705661&Fpath=&index=-1&l=zh .

陶显, 侯伟, 徐德.基于深度学习的表面缺陷检测方法综述[J/OL].自动化学报, 1-19[2020-06-19] . https://kns.cnki.net/KCMS/detail/11.2109.TP.20200402.1101.002.html https://kns.cnki.net/KCMS/detail/11.2109.TP.20200402.1101.002.html .

TAO X, HOU W, XU D. Asurvey of surface defect detection methods based on deep learning[J/OL]. Acta Automatica Sinica , 1-19[2020-06-19]. https://kns.cnki.net/KCMS/detail/11.2109.TP.20200402.1101.002.html https://kns.cnki.net/KCMS/detail/11.2109.TP.20200402.1101.002.html . (in Chinese)

李少波, 杨静, 王铮, 等.缺陷检测技术的发展与应用研究综述[J/OL].自动化学报, 1-18[2020-06-19].

LI S B, YANG J, WANG Z, et al . Review of development and application of defect detection technology[J/OL]. Acta Automatica Sinica , 1-18[2020-06-19]. (in Chinese)

L F CHEN , C T SU , M H CHEN , 等 . A neural-network approach for defect recognition in TFT-LCD photolithography process . IEEE Transactions on Electronics Packaging Manufacturing , 2009 . 32 ( 1 ): 1 - 8 . DOI: 10.1109/TEPM.2008.926117 http://doi.org/10.1109/TEPM.2008.926117 .

曾毅 , 郭龙源 , 罗百通 . 基于BP神经网络和均值差分的TFT-LCD MURA缺陷检测方法 . 湖南理工学院学报(自然科学版) , 2017 . 30 ( 1 ): 32 - 38 . http://www.cnki.com.cn/Article/CJFDTotal-YYSF201701007.htm http://www.cnki.com.cn/Article/CJFDTotal-YYSF201701007.htm .

Y ZENG , L Y GUO , B T LUO . TFT-LCD MURA defect detection method based on BP neural network and the mean difference . Journal of Hunan Institute of Science and Technology (Natural Sciences) , 2017 . 30 ( 1 ): 32 - 38 . http://www.cnki.com.cn/Article/CJFDTotal-YYSF201701007.htm http://www.cnki.com.cn/Article/CJFDTotal-YYSF201701007.htm .

欧先锋 , 晏鹏程 , 向灿群 , 等 . 基于FCN的TFT-LCD表面缺陷快速检测算法 . 成都工业学院学报 , 2017 . 20 ( 3 ): 6 - 10 . http://www.cqvip.com/QK/87678A/20173/673270284.html http://www.cqvip.com/QK/87678A/20173/673270284.html .

X F OU , P C YAN , C Q XIANG , 等 . Fast detection algorithm for TFT-LCD surface defects based on the full convolution neural networks . Journal of Chengdu Technological University , 2017 . 20 ( 3 ): 6 - 10 . http://www.cqvip.com/QK/87678A/20173/673270284.html http://www.cqvip.com/QK/87678A/20173/673270284.html .

何俊杰.基于深度学习的TFT-LCD线路缺陷检测研究[D].厦门: 厦门大学, 2018.

HE J J.Research on circuit defect detection of TFT-LCD based on deep learning[D]. Xiamen: Xiamen University, 2018. (in Chinese)

L MA , Y LU , X F NAN , 等 . Defect detection of mobile phone surface based on convolution neural network . DEStech Transactions on Computer Science and Engineering , 2018 . http://dpi-proceedings.com/index.php/dtcse/article/view/18645 http://dpi-proceedings.com/index.php/dtcse/article/view/18645 .

AKCAY S, ATAPOUR-ABARGHOUEI A, BRECKON T P, et al . GANomaly: semi-supervised anomaly detection via adversarial training[C]// Proceedings of the 14 th Asian Conference on Computer Vision . Perth: Springer, 2018.

The CIFAR-10 dataset[EB/OL]. https://www.cs.toronto.edu/~kriz/cifar.html https://www.cs.toronto.edu/~kriz/cifar.html .

LECUN Y, CORTES C, BURGES C J C. The MNIST database of handwritten digits[EB/OL]. http://yann.lecun.com/exdb/mnist/ http://yann.lecun.com/exdb/mnist/ .

ZHAO Z X, LI B, DONG R, et al . A surface defect detection method based on positive samples[C]// Proceedings of the 15 th Pacific Rim International Conference on Artificial Intelligence . Nanjing: Springer, 2018: 473-481.

G H HU , J F HUANG , Q H WANG , 等 . Unsupervised fabric defect detection based on a deep convolutional generative adversarial network . Textile Research Journal , 2020 . 90 ( 3-4 ): 247 - 270 . DOI: 10.1177/0040517519862880 http://doi.org/10.1177/0040517519862880 .

TANG H, XU D, SEBE N, et al . Attention-guided generative adversarial networks for unsupervised image-to-image translation[C]//2009 International Joint Conference on Neural Networks . Budapest: IEEE, 2019: 1-8.

TANG H, LIU H, XU D, et al . AttentionGAN: unpaired image-to-image translation using attention-guided generative adversarial networks[J]. arXiv preprint arXiv : 1911.11897, 2019.

L ITTI , C KOCH , E NIEBUR , 等 . A model of saliency-based visual attention for rapid scene analysis . IEEE Transactions on Pattern Analysis and Machine Intelligence , 1998 . 20 ( 11 ): 1254 - 1259 . DOI: 10.1109/34.730558 http://doi.org/10.1109/34.730558 .

L VINCENT . Morphological grayscale reconstruction in image analysis:applications and efficient algorithms . IEEE Transactions on Image Processing , 1993 . 2 ( 2 ): 176 - 201 . http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=217222 http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=217222 .

徐蔚波 , 刘颖 , 章浩伟 . 基于区域生长的图像分割研究进展 . 北京生物医学工程 , 2017 . 36 ( 3 ): 317 - 322 .

W B XU , Y LIU , H W ZHANG . Research progress in image segmentation based on region growing . Beijing Biomedical Engineering , 2017 . 36 ( 3 ): 317 - 322 .

高浩然. TFT-LCD制造中的阵列缺陷分析和修复[D].西安: 西安电子科技大学, 2010.

GAO H R. Array defects analysis and repair in TFT-LCD manufacturing[D]. Xi'an: Xidian University, 2010. (in Chinese)

GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al . Generative adversarial nets[C]// Proceedings of the 27 th International Conference on Neural Information Processing Systems . Cambridge: ACM, 2014: 2672-2680.

ISOLA P, ZHU J Y, ZHOU T H, et al . Image-to-image translation with conditional adversarial networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu: IEEE, 2017: 5967-5976.

ZHU J Y, PARK T, ISOLA P, et al . Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//2017 IEEE International Conference on Computer Vision . Venice: IEEE, 2017: 2242-2251.

YI Z L, ZHANG H, TAN P, et al . DualGAN: unsupervised dual learning for image-to-image translation[C]//2017 IEEE International Conference on Computer Vision . Venice: IEEE, 2017: 2868-2876.

KIM T, CHA M, KIM H, et al . Learning to discover cross-domain relations with generative adversarial networks[C]// Proceedings of the 34 th International Conference on Machine Learning . Sydney: ACM, 2017.

LIANG X D, ZHANG H, XING E P, et al . Generative semantic manipulation with contrasting GAN[J]. arXiv preprint arXiv : 1708.00315, 2017.

MO S, CHO M, SHIN J, et al . InstaGAN: instance-aware image-to-image translation[J] . arXiv preprint arXiv : 1812. 10889, 2018.

ZHANG H, GOODFELLOW I, METAXAS D, et al . Self-attention generative adversarial networks[J]. arXiv preprint arXiv : 1805. 08318, 2018.

ZHU J Y, ZHANG R, PATHAK D, et al . Toward multimodal image-to-image translation[C]// Proceedings of the 31 st International Conference on Neural Information Processing Systems . Red Hook: ACM, 2017: 465-476.

王永城 , 林珊玲 , 林志贤 , 等 . 基于自相关性和模版匹配的TFT缺陷电路重构算法 . 液晶与显示 , 2020 . 35 ( 6 ): 564 - 571 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=2194640&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=2194640&Fpath=&index=-1&l=zh .

Y C WANG , S L LIN , Z X LIN , 等 . TFT defect circuit reconstruction algorithm based on autocorrelation and template matching . Chinese Journal of Liquid Crystals and Displays , 2020 . 35 ( 6 ): 564 - 571 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=2194640&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=2194640&Fpath=&index=-1&l=zh .

MAO X D, LI Q, XIE H R, et al . Least squares generative adversarial networks[C]//2017 IEEE International Conference on Computer Vision . Venice: IEEE, 2017.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Development of AOI inspection of Mura defects on TFT-LCD surface

Defect detection of small object solder joints based on improved YOLOv7

DFNet： efficient decoder-free semantic segmentation networks

Influence of black photo spacer material for TFT-LCD on mark reading in exposure process

Effect of capacitance on common voltage in TFT-LCD

Related Author

CHEN Zekang

SHEN Yi

ZHAI Chenyang

DONG Chenyao

WANG Shuangxi

LIU Zhaolong

CAO Wei

GAO Junwei

Related Institution

Guangdong Provincial Key Laboratory of Automotive Display and Touch Technologies

College of Engineering， Shantou University

Shandong Key Laboratory of Industrial Control Technology

Qingdao International Airport Group Co. Ltd.

School of Automation， Qingdao University

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