基于视觉的液晶屏/OLED屏缺陷检测方法综述

Vision-based LCD/OLED defect detection methods:a critical summary

液晶屏(liquid crystal display, LCD)和有机发光半导体(organic light-emitting diode, OLED)屏的制造工艺复杂,其生产过程的每个阶段会不可避免地引入各种缺陷,影响产品的视觉效果及用户体验,甚至出现严重的质量问题。实现快速且精确的缺陷检测是提高产品质量和生产效率的重要手段。本文综述了近20年来基于机器视觉的液晶屏/OLED屏缺陷检测方法。首先给出了液晶屏/OLED屏表面缺陷的定义、分类及其产生的原因和缺陷的量化指标;指出了基于视觉的液晶屏/OLED屏表面缺陷检测的难点。然后重点阐述了基于图像处理的缺陷检测方法,包括介绍图像去噪和图像亮度矫正的图像预处理过程;考虑到所采集的液晶屏/OLED屏图像存在纹理背景干扰,对重复性纹理背景消除和背景抑制法进行分析;针对Mura缺陷边缘模糊等特点,总结改进的缺陷分割方法;阐述提取图像特征并使用支持向量机、支持向量数据描述和随机森林算法等基于特征识别的缺陷检测方法。接着综述了基于深度学习的缺陷检测方法,根据产线不同时期的样本数量分别总结了无监督学习、缺陷样本生成、迁移学习和监督学习的方法,其中无监督学习从基于生成对抗网络和自编码器两个方面进行阐述。随后梳理了通用纹理表面缺陷数据集和模型性能的评价指标。最后针对目前液晶屏/OLED屏缺陷检测方法存在的问题,对未来进一步的研究方向进行了展望。

The new display industry is an important foundation for strategic emerging information industries.Under the active guidance and continuous investment of various national industrial policies,China’s new display industry has rapidly developed and has become one of the most dynamic industries.The industry scale accounts for up to 40%of the global dis⁃play industry,ranking first in the world.Under the background of the current digital information age,the demand for con⁃sumer electronics,such as smart phones,tablets,computers,displays,and televisions,in various occasions,is con⁃stantly rising.This phenomenon results in a yearly rising trend in the global demand for liquid crystal display(LCD)and organic light-emitting diode(OLED)screens and other display panels.The manufacturing process of LCD and OLED is complex,and every stage of the production process will inevitably produce various defects,affecting the visual effect and user experience and even leading to serious quality problems.Fast and accurate defect detection is crucial to improving product quality and production efficiency.Therefore,the defect detection in the production process of LCD and OLED is necessary. This article reviews the research progress of defect detection methods for LCD/OLED based on machine vision inthe past 20 years to provide valuable reference. First, the structure and manufacturing process of commonly used TFT-LCDand OLED are given. The defects on the surface of the LCD/OLED are classified in accordance with the causes of defects,defect size, and defect shape. The definitions of the defects are presented, and the causes of the defects are brieflydescribed. The quantitative indicators of defects SEMU and DSEMU are given. The difficulties of surface defect detectionof LCD/OLED screens based on machine vision are also explained. This paper focuses on the defect detection methodsbased on image processing. In actual production, the images to be detected are captured by industrial cameras, and theirimages are easily affected by noise and light source. First, the image preprocessing of image denoising and image bright⁃ness correction is introduced. Then, eliminating the interference of texture background before segmentation and localiza⁃tion of defects is necessary due to the texture background of the collected LCD/OLED images. The repetitive texture back⁃ground elimination is elaborated, and the defect detection method based on background suppression method is introducedfrom the three methods of polynomial fitting, discrete cosine transform, and statistical analysis. The measurement stan⁃dards of background suppression are also presented. Mura defects are characterized by low contrast, blurred edges, andirregular shape. Thus, traditional edge detection and threshold segmentation methods are unsuitable for Mura defect seg⁃mentation, and achieving reliable detection of Mura defects is difficult. Therefore, improved defect segmentation methodsare introduced in three sections: threshold and cluster segmentation, active contour model-based method, and edge andshape detection. The evaluation indexes of defect segmentation effects are also given. Image features are the most basicattributes that characterize an image. One of the methods of defect detection is extracting and classifying local or global fea⁃tures of images. The defect detection methods based on feature recognition, which extract image features and use tradi⁃tional machine learning such as support vector machine, support vector data description, fuzzy pattern recognition, andrandom forest, are explained. Considering the traditional feature extraction method or the classical background reconstruc⁃tion method, the missing rate of low contrast and small area defects is still substantially high. The traditional defect detec⁃tion is conducted in multiple steps, which leads to the loss of defect information, resulting in the absence of low contrastdefect and restricting the detection accuracy. The poor expression capability of manually extracted features also leads to thelimitation of detection accuracy. In recent years, deep learning has achieved remarkable success in object detection, whichcan achieve fast and accurate target identification and detection. Thus, an increasing number of scholars have applied thismethod to the defect detection of LCD/OLED. This paper reviews the defect detection methods based on deep learning.According to the number of samples in different periods of production line, unsupervised and supervised learning, as wellas transfer learning and defect sample generation methods are summarized. Unsupervised learning based on deep learningincludes generative adversarial network and auto-encoder to learn the defect-free samples, reconstruct the defective imagein the test, and obtain the residual image for defect detection. Supervised learning requires a large number of defectsamples to overcome the problems of texture background interference, different defect sizes, and uneven samples. No pub⁃lic dataset based on display defects is currently available. This paper summarizes a series of general texture surface defectdata sets that can be used for texture-based background defect detection, which can be employed for transfer learning andalgorithm universality verification, and evaluation indicators of model performance are introduced. Finally, the existingproblems in the current LCD/OLED defect detection methods are identified. Complex background problems are stillunavoidable in the detection process due to the detection difficulties caused by the characteristics of Mura defects such aslow contrast and blurred edges. Limited datasets and real-time algorithm problems are also encountered. The futureresearch direction is prospected, and important research directions in the future include dataset expansion, sample equal⁃ization, enhanced algorithm generality, transferable algorithm, deep learning model acceleration, and curved screendefect detection. Such research direction may considerably promote the application of machine vision technology in LCD/OLED defect detection.