摘要
导光板是液晶显示屏背光模组的主要组成部分,在其生产过程中不可避免的会有部分导光板受到尖锐外力作用而产生线划伤缺陷,造成产品质量的下降。为了提升对该类缺陷检测的准确率,在分析导光板及其缺陷的光学特征基础上,本文提出了基于自适应的LoG滤波和残差卷积自动编码器的导光板线划伤缺陷的检测方法。首先,设计自适应的LoG滤波器对导光板图像进行边缘锐化,使缺陷和导光点与背景产生比较清晰的差异;其次,设计一种对导光板缺陷修复效果更好的残差卷积自动编码器,该自动编码器网络结构可以实现解码器部分对编码器部分的信息恒等共享,将锐化处理后的图像输入训练好的残差卷积自动编码器中,可以得到缺陷修复后的导光板图像;进而,将导光板图像和修复后图像做差,并进行全局阈值分割和区域特征筛选,可以准确提取出线划伤缺陷;最后,在工业现场采集的导光板图像上进行了大量的实验。实验结果表明,该算法的运行效率和准确率高,线划伤缺陷检测准确率可达98%。
The light guide plate is the main component of the backlight module of the liquid crystal display,during the process of installation and cleaning,it is inevitable that some light guide plates will be affected by sharp external forces and cause line scratch defects,which will cause decline of product quality.In order to improve the detection accuracy of this type of defect,on the basis of analyzing the optical characteristics of light guide plate and its defects,this paper proposes a detection method for line scratch defects on the light guide plate based on self-adapting LoG filter and residual convolutional autoencoder.First,to make the difference between the defect,the light guide point and the background clearer,an adaptive LoG filter is designed to sharpen the edges of the light guide plate image.Second,design a residual convolutional autoencoder which is better for repairing defects,the network structure of this autoencoder can make decoder identical share information from encoder,input the sharpened image to trained residual convolutional autoencoder and obtain defect repaired light guide plate image.And then,subtract light guide plate image from repaired image and accurately extract line scratch defects by performing global threshold segmentation and region feature selection.Finally,a lot of experiments are carried out on the light guide plate images collected at the industrial site.The experimental results show that this algorithm has high efficiency and accuracy,and the accuracy of line scratch defects detection can reach 98%.
作者
胡捷
李俊峰
HU Jie;LI Jun-feng(School of Mechanical Engineering and Automation,Zhejiang Sci-Tech University,Zhejiang Hangzhou 310018,China)
出处
《光电子．激光》
EI
CAS
CSCD
北大核心
2020年第8期825-833,共9页
Journal of Optoelectronics·Laser
基金
国家自然科学基金(61374022)
浙江省基础公益研究计划项目(LGG18F030001,GG19F030034)资助项目。
