参数自适应的液晶屏幕缺陷检测框架  

Parameter Adaptive LCD Screen Defect Detection Framework

作　　者：刘望 邵慧丽 何勇军[1] 谢怡宁[1] 陈德运[1] LIU Wang;SHAO Hui-li;HE Yong-jun;XIE Yi-ning;CHEN De-yun(School of Computer Science and Technology,Harbin University of Science and Technology,Harbin 150080,China)

机构地区：[1]哈尔滨理工大学计算机科学与技术学院,哈尔滨150080

出　　处：《哈尔滨理工大学学报》2020年第5期75-82,共8页Journal of Harbin University of Science and Technology

基　　金：黑龙江省教育厅科学技术研究面上项目(12511101)。

摘　　要：液晶显示屏生产过程中不可避免存在缺陷,需要检测以确保质量。人工检测工作量大、准确率低、迫切需要一种高效而准确的自动化检测方法。为此,提出了一种新的参数自适应的缺陷检测框架,主要包括提取屏幕区域、预处理、阈值分割、缺陷选择。通过参数的自适应调整,使检测方法适应各种复杂的情况。在阈值分割时,针对光照影响的问题,采用自适应调整阈值参数的方式分割缺陷区域。首先计算图像的最大灰度值,然后根据无缺陷图像确定固定参数,缺陷图像确定系数,最后在固定参数和最大灰度值与系数之积中选择最大值作为阈值分割的最小阈值。在检测饱和度缺陷时,针对低分辨率相机拍摄的图像明暗差异小的问题,采用自适应调整曝光参数采集图像分别处理明暗程度差异大的不同图像部分。实验表明,该方法能高效准确地检测点类、线类、Mura和饱和度缺陷。It is necessary to detect defects in the production process of LCD screens for quality improvements. Manual detection brings a heavy workload and low accuracy. Therefore, an efficient and accurate automatic detection method is urgently needed. To this end, this paper proposes a new defect detection framework, which mainly includes screen area extraction, preprocessing, threshold segmentation and defect selection. By adaptive adjustment of parameters, the detection method can adapt to various complex situations. In order to eliminate the influence of illumination changes, the defect region is segmented by automatic parameter adjustment in the threshold segmentation. First, the maximum grayscale value of the image is calculated, and then the fixed parameters and the coefficient of the defect image are determined according to the no-defect image, and finally the maximum value which was selected as the minimum threshold of the threshold segmentation from the fixed parameters and the product of the maximum grayscale value and the coefficient. In addition, in order to solve the problem that the brightness difference of the images captured by low-resolution cameras is too small to detect defects in the saturation condition, self-adaptive adjustment of exposure parameters was used to collect images to process different parts of images with large difference in light and shade. Experiments show that the method can achieve high performance and efficiency in detecting defects such as points, lines, Mura, saturation.

关 键 词：缺陷检测 高斯差分滤波 饱和度 参数自适应 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]