基于AttentionGAN和形态学重建的TFT阵列缺陷检测  

TFT array defect detection based on AttentionGAN and morphological reconstruction

作　　者：陈炜炜 严群 姚剑敏[1,2] CHEN Wei-wei;YAN Qun;YAO Jian-min(College of Physics and Information Engineering, Fuzhou University, Fuzhou 350108, China;Jinjiang RichSense Electronic Technology Co., Ltd., Jinjiang 362200, China)

机构地区：[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

出　　处：《液晶与显示》2020年第12期1270-1277,共8页Chinese Journal of Liquid Crystals and Displays

基　　金：国家重点研发计划课题(No.2016YFB0401503);广东省科技重大专项(No.2016B090906001);福建省科技重大专项(No.2014HZ0003-1);广东省光信息材料与技术重点实验室开放基金(No.2017B030301007)。

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。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：TFT-LCD 缺陷检测 生成式对抗网络 形态学重建 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术] TH691.9[自动化与计算机技术—计算机科学与技术]