高精度小视野TFT-LCD图像异物缺陷自动分割  

Automatic Segmentation of Defect in High-Precision and Small-Field TFT-LCD Images

作　　者：杨勍[1] 赵于前[1,2] 张帆 廖苗[1] Yang Qing;Zhao Yuqian;Zhang Fan;Liao Miao(School of Automation,Central South University,Changsha 410083,Hunan,China;Hunan Engineering and Technology Research Center of High Strength Fastener Intelligent Manufacturing,Changde 415701,Hunan,China)

机构地区：[1]中南大学自动化学院,湖南长沙410083 [2]湖南省高强度紧固件智能制造工程技术研究中心,湖南常德415701

出　　处：《激光与光电子学进展》2022年第12期304-311,共8页Laser & Optoelectronics Progress

摘　　要：为了精确分割TFT-LCD异物缺陷,准确计算缺陷尺寸,满足TFT-LCD工业生产中对异物缺陷检测的需求,提出一种面向高精度小视野TFT-LCD图像的异物缺陷高精度自动分割方法。首先,根据屏幕像素的空间分布规律,考虑缺陷的尺寸变化,采用基于空间信息多尺度显著性的缺陷提取方法,自动获得图像中的缺陷区域。然后,结合缺陷与屏幕像素间隙的空间分布关系,找到被像素间隙截断的对应缺陷块组。最后,利用局部凸包拟合算法对缺陷区域进行连通,实现对异物缺陷的自动分割。实验结果证明,所提方法能较精确地分割异物缺陷,精确率和召回率分别为95.36%和93.34%,且尺寸计算正确率为96.5%,基本满足工业生产中TFT-LCD异物缺陷尺寸计算的稳定可靠、高精度、高准确性等要求。In this paper, we propose a high-precision automatic segmentation method for foreign body defects in high-precision small-field TFT-LCD images to segment TFT-LCD foreign body defects and calculate their size accurately, meeting the requirements of foreign matter defect detection in TFT-LCD industrial production. First,using the spatial distribution of screen pixels and considering the dimensional change of defects, we employ the defect extraction method based on spatial information multiscale saliency detection to automatically obtain the defect areas on the image. Next, combining the spatial distribution relationship between the defects and the gap of screen pixels, the corresponding defect block group truncated by pixel gap is found. Finally, a local convex hull fitting algorithm is used to connect the defect areas to realize automatic segmentation for foreign body defects.Experimental results show that the proposed method can segment foreign body defects more accurately, attaining the accuracy and recall rate of 95. 36% and 93. 34%, respectively. Furthermore, it obtains the correct size calculation rate of 96. 5%, which meets the requirements of TFT-LCD foreign body defect size calculation in industrial production stability, reliability, high precision, high accuracy, and other requirements.

关 键 词：机器视觉 TFT-LCD 缺陷分割 显著性检测 凸包拟合 

分 类 号：O436[机械工程—光学工程]