浏览全部资源
扫码关注微信
Published： 16 May 2024 ，
移动端阅览
林思媛， 吴一全. 2024. 基于视觉的液晶屏/OLED屏缺陷检测方法综述. 中国图象图形学报， 29(05):1321-1345
Lin Siyuan， Wu Yiquan. 2024. Vision-based LCD/OLED defect detection methods： a critical summary. Journal of Image and Graphics， 29(05):1321-1345
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 display industry， ranking first in the world. Under the background of the current digital information age， the demand for consumer electronics， such as smart phones， tablets， computers， displays， and televisions， in various occasions， is constantly 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 in the past 20 years to provide valuable reference. First， the structure and manufacturing process of commonly used TFT-LCD and 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 briefly described. The quantitative indicators of defects SEMU and DSEMU are given. The difficulties of surface defect detection of LCD/OLED screens based on machine vision are also explained. This paper focuses on the defect detection methods based on image processing. In actual production， the images to be detected are captured by industrial cameras， and their images are easily affected by noise and light source. First， the image preprocessing of image denoising and image brightness correction is introduced. Then， eliminating the interference of texture background before segmentation and localization of defects is necessary due to the texture background of the collected LCD/OLED images. The repetitive texture background elimination is elaborated， and the defect detection method based on background suppression method is introduced from the three methods of polynomial fitting， discrete cosine transform， and statistical analysis. The measurement standards of background suppression are also presented. Mura defects are characterized by low contrast， blurred edges， and irregular shape. Thus， traditional edge detection and threshold segmentation methods are unsuitable for Mura defect segmentation， and achieving reliable detection of Mura defects is difficult. Therefore， improved defect segmentation methods are introduced in three sections： threshold and cluster segmentation， active contour model-based method， and edge and shape detection. The evaluation indexes of defect segmentation effects are also given. Image features are the most basic attributes that characterize an image. One of the methods of defect detection is extracting and classifying local or global features of images. The defect detection methods based on feature recognition， which extract image features and use traditional machine learning such as support vector machine， support vector data description， fuzzy pattern recognition， and random forest， are explained. Considering the traditional feature extraction method or the classical background reconstruction method， the missing rate of low contrast and small area defects is still substantially high. The traditional defect detection is conducted in multiple steps， which leads to the loss of defect information， resulting in the absence of low contrast defect and restricting the detection accuracy. The poor expression capability of manually extracted features also leads to the limitation of detection accuracy. In recent years， deep learning has achieved remarkable success in object detection， which can achieve fast and accurate target identification and detection. Thus， an increasing number of scholars have applied this method 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 well as transfer learning and defect sample generation methods are summarized. Unsupervised learning based on deep learning includes generative adversarial network and auto-encoder to learn the defect-free samples， reconstruct the defective image in the test， and obtain the residual image for defect detection. Supervised learning requires a large number of defect samples to overcome the problems of texture background interference， different defect sizes， and uneven samples. No public dataset based on display defects is currently available. This paper summarizes a series of general texture surface defect data sets that can be used for texture-based background defect detection， which can be employed for transfer learning and algorithm universality verification， and evaluation indicators of model performance are introduced. Finally， the existing problems in the current LCD/OLED defect detection methods are identified. Complex background problems are still unavoidable in the detection process due to the detection difficulties caused by the characteristics of Mura defects such as low contrast and blurred edges. Limited datasets and real-time algorithm problems are also encountered. The future research direction is prospected， and important research directions in the future include dataset expansion， sample equalization， enhanced algorithm generality， transferable algorithm， deep learning model acceleration， and curved screen defect detection. Such research direction may considerably promote the application of machine vision technology in LCD/ OLED defect detection.
缺陷检测液晶屏（LCD）OLED屏机器视觉深度学习纹理背景消除无监督学习
defect detectionliquid crystal display（LCD）organic light emitting diode （OLED）machine visiondeep learningtexture background eliminationunsupervised learning
Aiger D and Talbot H. 2010. The phase only transform for unsupervised surface defect detection//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco， USA： IEEE： 295-302 ［DOI： 10.1109/CVPR.2010.5540198http://dx.doi.org/10.1109/CVPR.2010.5540198］
Badrinarayanan V， Kendall A and Cipolla R. 2017. SegNet： a deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence， 39（12）： 2481-2495 ［DOI： 10.1109/TPAMI.2016.2644615http://dx.doi.org/10.1109/TPAMI.2016.2644615］
Bergmann P， Fauser M， Sattlegger D and Steger C. 2019. MVTec AD： a comprehensive real-world dataset for unsupervised anomaly detection//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Long Beach， USA： IEEE： 9584-9592 ［DOI： 10.1109/CVPR.2019.00982http://dx.doi.org/10.1109/CVPR.2019.00982］
Bhalla K and Huang Y P. 2021. An adaptive thresholding based method to locate and segment defects on LCD panels//Proceedings of 2021 International Conference on System Science and Engineering （ICSSE）. Ho Chi Minh City， Vietnam： IEEE： 328-333 ［DOI： 10.1109/ICSSE52999.2021.9538470http://dx.doi.org/10.1109/ICSSE52999.2021.9538470］
Bi X and Ding H. 2010. Machine vision inspection method of Mura defect for TFT-LCD. Journal of Mechanical Engineering， 46（12）： 13-19
毕昕， 丁汉. 2010. TFT-LCD Mura缺陷机器视觉检测方法. 机械工程学报， 46（12）： 13-19 ［DOI： 10.3901/JME.2010.12.013http://dx.doi.org/10.3901/JME.2010.12.013］
Bi X， Zhuang C G and Ding H. 2009. A new Mura defect inspection way for TFT-LCD using level set method. IEEE Signal Processing Letters， 16（4）： 311-314 ［DOI： 10.1109/LSP.2009.2014113http://dx.doi.org/10.1109/LSP.2009.2014113］
Cen Y G， Zhao R Z， Cen L H， Cui L H， Miao Z J and Wei Z. 2015. Defect inspection for TFT-LCD images based on the low-rank matrix reconstruction. Neurocomputing， 149： 1206-1215 ［DOI： 10.1016/j.neucom.2014.09.007http://dx.doi.org/10.1016/j.neucom.2014.09.007］
Chen F C， Fang L T， Lee L， Wen C H， Cheng S Y and Wang S J. 2005. LOG-filter-based inspection of cluster Mura and vertical-band Mura on liquid crystal displays//Proceedings Volume 5679， Machine Vision Applications in Industrial Inspection XIII. San Jose， USA： SPIE： 257-265 ［DOI： 10.1117/12.586688http://dx.doi.org/10.1117/12.586688］
Chen L C and Kuo C C. 2008. Automatic TFT-LCD Mura defect inspection using discrete cosine transform-based background filtering and ‘just noticeable difference’ quantification strategies. Measurement Science and Technology， 19（1）： #015507 ［DOI： 10.1088/0957-0233/19/1/015507http://dx.doi.org/10.1088/0957-0233/19/1/015507］
Chen M F， Chen P， Wang S， Cui Y， Zhang Y X and Chen S L. 2022. TFT-LCD Mura defect visual inspection method in multiple backgrounds. Journal of the Society for Information Display， 30（11）： 818-831 ［DOI： 10.1002/jsid.1171http://dx.doi.org/10.1002/jsid.1171］
Chen S L and Chou S T. 2008. TFT-LCD Mura defect detection using wavelet and cosine transforms. Journal of Advanced Mechanical Design， Systems， and Manufacturing， 2（3）： 441-453 ［DOI： 10.1299/jamdsm.2.441http://dx.doi.org/10.1299/jamdsm.2.441］
Cimpoi M， Maji S， Kokkinos I， Mohamed S and Vedaldi A. 2014. Describing textures in the wild//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus， USA： IEEE： 3606-3613 ［DOI： 10.1109/CVPR.2014.461http://dx.doi.org/10.1109/CVPR.2014.461］
Dai C D， Xu G L， Mao J， Gu T and Luo J Y. 2021. Cell phone screen defect segmentation based on unsupervised network. Laser and Optoelectronics Progress， 58（20）： #2015003
代朝东， 许国良， 毛骄， 顾桐， 雒江涛. 2021. 基于无监督网络的手机屏幕缺陷分割方法. 激光与光电子学进展， 58（20）： #2015003 ［DOI： 10.3788/LOP202158.2015003http://dx.doi.org/10.3788/LOP202158.2015003］
Du Y D， Feng L， Tao P， Gong X and Wang J. 2023. Meta-transfer learning in cross-domain image classification with few-shot learning. Journal of Image and Graphics， 28（9）： 2899-2912
杜彦东， 冯林， 陶鹏， 龚勋， 王俊. 2023. 元迁移学习在少样本跨域图像分类中的研究. 中国图象图形学报， 28（9）： 2899-2912 ［DOI： 10.11834/jig.220664http://dx.doi.org/10.11834/jig.220664］
Fan X H. 2022. Research on Surface Defect Detection Method of LCD Screen Based on Deep Learning. Anqing： Anqing Normal University
范旭辉. 2022. 基于深度学习的液晶屏表面缺陷检测方法研究. 安庆： 安庆师范大学 ［DOI： 10.27761/d.cnki.gaqsf.2022.000254http://dx.doi.org/10.27761/d.cnki.gaqsf.2022.000254］
Fang L T， Chen H C， Yin I C， Wang S J， Wen C H and Kuo C H. 2006. Automatic Mura detection system for liquid crystal display panels//Proceedings Volume 6070， Machine Vision Applications in Industrial Inspection XIV. San Jose， USA： SPIE： 143-152 ［DOI： 10.1117/12.650686http://dx.doi.org/10.1117/12.650686］
Gan Y Z and Zhao Q F. 2013. An effective defect inspection method for LCD using active contour model. IEEE Transactions on Instrumentation and Measurement， 62（9）： 2438-2445 ［DOI： 10.1109/TIM.2013.2258242http://dx.doi.org/10.1109/TIM.2013.2258242］
Goodfellow I， Pouget-Abadie J， Mirza M， Xu B， Warde-Farley D， Ozair S， Courville A and Bengio Y. 2020. Generative adversarial networks. Communications of the ACM， 63（11）： 139-144 ［DOI： 10.1145/3422622http://dx.doi.org/10.1145/3422622］
He K M， Zhang X Y， Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Las Vegas， USA： IEEE： 770-778 ［DOI： 10.1109/CVPR.2016.90http://dx.doi.org/10.1109/CVPR.2016.90］
He Z Y and Sun L N. 2015. Surface defect detection method for glass substrate using improved Otsu segmentation. Applied Optics， 54（33）： 9823-9830 ［DOI： 10.1364/AO.54.009823http://dx.doi.org/10.1364/AO.54.009823］
Hecht S. 1924. The visual discrimination of intensity and the Weber-Fechner law. The Journal of General Physiology， 7（2）： 235-267 ［DOI： 10.1085/jgp.7.2.235http://dx.doi.org/10.1085/jgp.7.2.235］
Hinton G E and Salakhutdinov R R. 2006. Reducing the dimensionality of data with neural networks. Science， 313（5786）： 504-507 ［DOI： 10.1126/science.1127647http://dx.doi.org/10.1126/science.1127647］
Huang G， Liu Z， van der Maaten L and Weinberger K Q. 2017. Densely connected convolutional networks//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu， USA： IEEE： 2261-2269 ［DOI： 10.1109/CVPR.2017.243http://dx.doi.org/10.1109/CVPR.2017.243］
Jazi A Y， Liu J J and Lee H. 2012. Automatic inspection of TFT-LCD glass substrates using optimized support vector machines. IFAC Proceedings Volumes， 45（15）： 325-330 ［DOI： 10.3182/20120710-4-SG-2026.00054http://dx.doi.org/10.3182/20120710-4-SG-2026.00054］
Jian C X. 2015. Review of TFT-LCD surface defect detection methods. Video Engineering， 39（9）： 146-152
简川霞. 2015. TFT-LCD表面缺陷检测方法综述. 电视技术， 39（9）： 146-152 ［DOI： 10.16280/j.videoe.2015.09.034http://dx.doi.org/10.16280/j.videoe.2015.09.034］
Jian C X， Wang H M， Xu J J， Su L H and Wang T P. 2021. Automatic surface defect detection for OLED display. Packaging Engineering， 42（13）： 280-287
简川霞， 王华明， 徐进军， 苏林海， 王太平. 2021. OLED显示屏表面缺陷自动检测方法. 包装工程， 42（13）： 280-287 ［DOI： 10.19554/j.cnki.1001-3563.2021.13.039http://dx.doi.org/10.19554/j.cnki.1001-3563.2021.13.039］
Jin S Q， Ji C， Yan C C and Xing J Y. 2018. TFT-LCD Mura defect detection using DCT and the dual-γ piecewise exponential transform. Precision Engineering， 54： 371-378 ［DOI： 10.1016/j.precisioneng.2018.07.006http://dx.doi.org/10.1016/j.precisioneng.2018.07.006］
Kang S B， Lee J H， Song K Y and Pahk H J. 2009. Automatic defect classification of TFT-LCD panels using machine learning//Proceedings of 2009 IEEE International Symposium on Industrial Electronics. Seoul， Korea （South）： IEEE： 2175-2177 ［DOI： 10.1109/ISIE.2009.5213760http://dx.doi.org/10.1109/ISIE.2009.5213760］
Krizhevsky A， Sutskever I and Hinton G. 2017. ImageNet classification with deep convolutional neural networks. Communications of the ACM， 60（6）： 84-90 ［DOI： 10.1145/3065386http://dx.doi.org/10.1145/3065386］
Lee J Y and Yoo S I. 2004. Automatic detection of region-Mura defect in TFT-LCD. IEICE Transactions on Information and Systems， 87（10）： 2371-2378
Lee M C H， Petersen K， Pawlowski N， Glocker B and Schaap M. 2019. TETRIS： template Transformer networks for image segmentation with shape priors. IEEE Transactions on Medical Imaging， 38（11） 2596-2606 ［DOI： 10.1109/TMI.2019.2905990http://dx.doi.org/10.1109/TMI.2019.2905990］
Lei J， Gao X， Feng Z L， Qiu H M and Song M L. 2018. Scale insensitive and focus driven mobile screen defect detection in industry. Neurocomputing， 294： 72-81 ［DOI： 10.1016/j.neucom.2018.03.013http://dx.doi.org/10.1016/j.neucom.2018.03.013］
Li C M， Kao C Y， Gore J C and Ding Z H. 2007. Implicit active contours driven by local binary fitting energy//Proceedings of 2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis， USA： IEEE： #383014 ［DOI： 10.1109/CVPR.2007.383014http://dx.doi.org/10.1109/CVPR.2007.383014］
Li C M， Kao C Y， Gore J C and Ding Z H. 2008. Minimization of region scalable fitting energy for image segmentation. IEEE Transactions on Image Processing， 17（10）： 1940-1949 ［DOI： 10.1109/TIP.2008.2002304http://dx.doi.org/10.1109/TIP.2008.2002304］
Li K， Li H， Liu Y J， Liang P and Lu X P. 2014. Background suppression of LCD Mura defect using B-spline surface fitting. Opto-Electronic Engineering， 41（2）： 33-39
李坤， 李辉， 刘云杰， 梁平， 卢小鹏. 2014. LCD Mura缺陷的B样条曲面拟合背景抑制. 光电工程， 41（2）： 33-39 ［DOI： 10.3969/j.issn.1003-501X.2014.02.006http://dx.doi.org/10.3969/j.issn.1003-501X.2014.02.006］
Li W C and Tsai D M. 2011. Defect inspection in low-contrast LCD images using Hough transform-based nonstationary line detection. IEEE Transactions on Industrial Informatics， 7（1）： 136-147 ［DOI： 10.1109/TII.2009.2034844http://dx.doi.org/10.1109/TII.2009.2034844］
Liang J F， Li T， Yang J Q， Li Y N， Fang Z W and Yang F. 2023. Video anomaly detection by fusing self-attention and autoencoder. Journal of Image and Graphics， 28（4）： 1029-1040
梁家菲， 李婷， 杨佳琪， 李亚楠， 方智文， 杨丰. 2023. 融合自注意力和自编码器的视频异常检测. 中国图象图形学报， 28（4）： 1029-1040 ［DOI： 10.11834/jig.211147http://dx.doi.org/10.11834/jig.211147］
Lin G M， Kong L F， Liu T J， Qiu L D and Chen X Y. 2022. An antagonistic training algorithm for TFT-LCD module Mura defect detection. Signal Processing： Image Communication， 107： #116791 ［DOI： 10.1016/j.image.2022.116791http://dx.doi.org/10.1016/j.image.2022.116791］
Lin T Y， Goyal P， Girshick R， He K M and Dollr P. 2020. Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence， 42（2）： 318-327 ［DOI： 10.1109/TPAMI.2018.2858826http://dx.doi.org/10.1109/TPAMI.2018.2858826］
Liu J Y， Wu H， Liu Y L and Wang J C. 2022. Automatic generation and detection method of LCD samples based on deep learning//Proceedings of the 5th World Conference on Mechanical Engineering and Intelligent Manufacturing （WCMEIM）. Ma’anshan， China： IEEE： 724-730 ［DOI： 10.1109/WCMEIM56910.2022.10021421http://dx.doi.org/10.1109/WCMEIM56910.2022.10021421］
Liu Q. 2020. Research on Visual Inspection Technology for Display Defects of New Array Panel. Harbin： Harbin Institute of Technology
刘强. 2020. 新型阵列屏体的显示缺陷视觉检测技术研究. 哈尔滨： 哈尔滨工业大学 ［DOI： 10.27061/d.cnki.ghgdu.2020.006330http://dx.doi.org/10.27061/d.cnki.ghgdu.2020.006330］
Liu W， Anguelov D， Erhan D， Szegedy C， Reed S， Fu C Y and Berg A C. 2016. SSD： single shot MultiBox detector//Proceedings of the 14th European Conference on Computer Vision. Amsterdam， The Netherlands： Springer： 21-37 ［DOI： 10.1007/978-3-319-46448-0_2http://dx.doi.org/10.1007/978-3-319-46448-0_2］
Liu Y H and Chen Y J. 2011. Automatic defect detection for TFT-LCD array process using quasiconformal kernel support vector data description. International Journal of Molecular Sciences， 12（9）： 5762-5781 ［DOI： 10.3390/ijms12095762http://dx.doi.org/10.3390/ijms12095762］
Liu Y H， Huang Y K and Lee M J. 2008. Automatic inline defect detection for a thin film transistor—liquid crystal display array process using locally linear embedding and support vector data description. Measurement Science and Technology， 19（9）： #095501 ［DOI： 10.1088/0957-0233/19/9/095501http://dx.doi.org/10.1088/0957-0233/19/9/095501］
Liu Y H， Lin S H， Hsueh Y L and Lee M J. 2009a. Automatic target defect identification for TFT-LCD array process inspection using kernel FCM-based fuzzy SVDD ensemble. Expert Systems with Applications， 36（2）： 1978-1998 ［DOI： 10.1016/j.eswa.2007.12.015http://dx.doi.org/10.1016/j.eswa.2007.12.015］
Liu Y H， Liu Y C and Chen Y Z. 2011. High-speed inline defect detection for TFT-LCD array process using a novel support vector data description. Expert Systems with Applications， 38（5）： 6222-6231 ［DOI： 10.1016/j.eswa.2010.11.046http://dx.doi.org/10.1016/j.eswa.2010.11.046］
Liu Y H， Wang C K， Ting Y， Lin W Z， Kang Z H， Chen C S and Hwang J S. 2009b. In-TFT-array-process micro defect inspection using nonlinear principal component analysis. International Journal of Molecular Sciences， 10（10）： 4498-4514 ［DOI： 10.3390/ijms10104498http://dx.doi.org/10.3390/ijms10104498］
Lu C J and Tsai D M. 2005. Automatic defect inspection for LCDs using singular value decomposition. The International Journal of Advanced Manufacturing Technology， 25（1/2）： 53-61 ［DOI： 10.1007/s00170-003-1832-6http://dx.doi.org/10.1007/s00170-003-1832-6］
Lu C J and Tsai D M. 2008. Independent component analysis-based defect detection in patterned liquid crystal display surfaces. Image and Vision Computing， 26（7）： 955-970 ［DOI： 10.1016/j.imavis.2007.10.007http://dx.doi.org/10.1016/j.imavis.2007.10.007］
Lu H P and Su C T. 2021. CNNs combined with a conditional GAN for Mura defect classification in TFT-LCDs. IEEE Transactions on Semiconductor Manufacturing， 34（1）： 25-33 ［DOI： 10.1109/TSM.2020.3048631http://dx.doi.org/10.1109/TSM.2020.3048631］
Lu X P. 2014. Study on the Methods of Machine Vision Inspection for the Mura Defect of TFT-LCD. Chengdu： University of Electronic Science and Technology of China
卢小鹏. 2014. TFT-LCD Mura缺陷机器视觉检测方法研究. 成都： 电子科技大学
Lu X P， Li H， Liu Y J， Liang P and Li K. 2014. Algorithm for fast TFT-LCD Mura defect image segmentation based on Chan-Vese model. Chinese Journal of Liquid Crystals and Displays， 29（1）： 146-151
卢小鹏， 李辉， 刘云杰， 梁平， 李坤. 2014. 基于Chan-Vese模型的TFT-LCD Mura缺陷快速分割算法. 液晶与显示， 29（1）： 146-151 ［DOI： 10.3788/YJYXS20142901.0146http://dx.doi.org/10.3788/YJYXS20142901.0146］
Lu Y， Ma L and Jiang H Q. 2020. A light CNN model for defect detection of LCD//Frontier Computing （FC 2019）. Singapore， Singapore： Springer： 10-19 ［DOI： 10.1007/978-981-15-3250-4_2http://dx.doi.org/10.1007/978-981-15-3250-4_2］
Mallikarjuna P， Targhi A T， Fritz M， Hayman E， Caputo B and Eklundh J O. 2006. The KTH-TIPS2 database. Stockholm， Sweden： Computational Vision and Active Perception Laboratory， School of Computer Science and Communication
Mei S. 2017. Research on TFT-LCD Mura Defect Recognition Based on Deep Learning. Wuhan： Huazhong University of Science and Technology
梅爽. 2017. 基于深度学习的液晶屏Mura缺陷图像识别算法研究. 武汉： 华中科技大学
Mei S， Yang H and Yin Z P. 2017. Unsupervised-learning-based feature-level fusion method for Mura defect recognition. IEEE Transactions on Semiconductor Manufacturing， 30（1）： 105-113 ［DOI： 10.1109/TSM.2017.2648856http://dx.doi.org/10.1109/TSM.2017.2648856］
Mei S， Yang H and Yin Z P. 2018. An unsupervised-learning-based approach for automated defect inspection on textured surfaces. IEEE Transactions on Instrumentation and Measurement， 67（6）： 1266-1277 ［DOI： 10.1109/TIM.2018.2795178http://dx.doi.org/10.1109/TIM.2018.2795178］
Ming W Y， Zhang S F， Liu X W， Liu K， Yuan J， Xie Z B， Sun P Y and Guo X D. 2021. Survey of Mura defect detection in liquid crystal displays based on machine vision. Crystals， 11（12）： #1444 ［DOI： 10.3390/cryst11121444http://dx.doi.org/10.3390/cryst11121444］
Nakano H and Mori Y. 2005. Measurement method for low-contrast nonuniformity in liquid crystal displays by using multi-wavelet analysis//Proceedings Volume 5880， Optical Diagnostics. San Diego， USA： SPIE： 313-318 ［DOI： 10.1117/12.616232http://dx.doi.org/10.1117/12.616232］
Oh J H， Yun B J and Park K H. 2007. The defect detection using human visual system and wavelet transform in TFT-LCD image//2007 Frontiers in the Convergence of Bioscience and Information Technologies. Jeju， Korea （South）： IEEE： 498-503 ［DOI： 10.1109/FBIT.2007.49http://dx.doi.org/10.1109/FBIT.2007.49］
Ouyang T. 2018. Research and Implementation of Defect Detection Algorithm for OLED Display. Shanghai： Shanghai Jiao Tong University
欧阳韬. 2018. OLED显示屏缺陷检测算法的研究与实现. 上海： 上海交通大学
Peng D Q， Liu H and Xu G L. 2021. Object segmentation algorithm modified by candidate box for fully convolution network. Journal of Chongqing University of Posts and Telecommunications （Natural Science Edition）， 33（1）： 135-143
彭大芹， 刘恒， 许国良. 2021. 使用候选框进行全卷积网络修正的目标分割算法. 重庆邮电大学学报（自然科学版）， 33（1）： 135-143 ［DOI： 10.3979/j.issn.1673-825X.201903210099http://dx.doi.org/10.3979/j.issn.1673-825X.201903210099］
Pratt W K， Sawkar S S and O’Reilly K. 1998. Automatic blemish detection in liquid crystal flat panel displays//Proceedings Volume 3306， Machine Vision Applications in Industrial Inspection VI. San Jose， USA： SPIE： 2-13 ［DOI： 10.1117/12.301232http://dx.doi.org/10.1117/12.301232］
Qian J D， Chen B， Qian J Y， Zhao H J and Chen G. 2018. Machine vision based inspection method of Mura defect for LCD. Computer Science， 45（6）： 296-300， 313
钱基德， 陈斌， 钱基业， 赵恒军， 陈刚. 2018. 基于机器视觉的液晶屏Mura缺陷检测方法. 计算机科学， 45（6）： 296-300， 313 ［DOI： 10.11896/j.issn.1002-137X.2018.06.052http://dx.doi.org/10.11896/j.issn.1002-137X.2018.06.052］
Redmon J， Divvala S， Girshick R and Farhadi A. 2016. You only look once： unified， real-time object detection//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas， USA： IEEE： 779-788 ［DOI： 10.1109/CVPR.2016.91http://dx.doi.org/10.1109/CVPR.2016.91］
Ren S Q， He K M， Girshick R and Sun J. 2017. Faster R-CNN： towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence， 39（6）： 1137-1149 ［DOI： 10.1109/TPAMI.2016.2577031http://dx.doi.org/10.1109/TPAMI.2016.2577031］
Ronneberger O， Fischer P and Brox T. 2015. U-Net： convolutional networks for biomedical image segmentation//Proceedings of the 18th Medical Image Computing and Computer-Assisted Intervention. Munich， Germany： Springer： 234-241 ［DOI： 10.1007/978-3-319-24574-4_28http://dx.doi.org/10.1007/978-3-319-24574-4_28］
SEMI. 2002. SEMI D31-1102： Definition of measurement index （Semu） for luminance Mura in FPD image quality inspection//Japan FPD Metrology Committee Meeting Minutes. Yokohama， Japan
Sharan L， Rosenholtz R and Adelson E H. 2014. Accuracy and speed of material categorization in real-world images. Journal of Vision， 14（9）： #12 ［DOI： 10.1167/14.9.12http://dx.doi.org/10.1167/14.9.12］
Shelhamer E， Long J and Darrell T. 2017. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence， 39（4）： 640-651 ［DOI： 10.1109/TPAMI.2016.2572683http://dx.doi.org/10.1109/TPAMI.2016.2572683］
Shuai L Y， Chen H X and Wang Z X. 2022. Defect detection of four-color display screen based on color equalization and local dynamic threshold segmentation//Proceedings of AIIPCC 2022， the 3rd International Conference on Artificial Intelligence， Information Processing and Cloud Computing. Online： VDE： 1-5
Song K Y. 2021. Research on Visual Inspection Algorithm of Mura Defects Based on Deep Feature Encoding. Wuhan： Huazhong University of Science and Technology
宋开友. 2021. 基于深度特征编码的Mura缺陷视觉检测算法研究. 武汉： 华中科技大学 ［DOI： 10.27157/d.cnki.ghzku.2021.006214http://dx.doi.org/10.27157/d.cnki.ghzku.2021.006214］
Song K Y， Yang H and Yin Z P. 2021a. Multi-scale boosting feature encoding network for texture recognition. IEEE Transactions on Circuits and Systems for Video Technology， 31（11）： 4269-4282 ［DOI： 10.1109/TCSVT.2021.3051003http://dx.doi.org/10.1109/TCSVT.2021.3051003］
Song K Y， Yang H and Yin Z P. 2022. Anomaly composition and decomposition network for accurate visual inspection of texture defects. IEEE Transactions on Instrumentation and Measurement， 71： #5017814 ［DOI： 10.1109/TIM.2022.3196133http://dx.doi.org/10.1109/TIM.2022.3196133］
Song S B， Yang K C， Wang A N， Zhang S S and Xia M. 2021b. A Mura detection model based on unsupervised adversarial learning. IEEE Access， 9： 49920-49928 ［DOI： 10.1109/ACCESS.2021.3069466http://dx.doi.org/10.1109/ACCESS.2021.3069466］
Tan M X and Le Q V. 2019. EfficientNet： rethinking model scaling for convolutional neural networks//Proceedings of the 36th International Conference on Machine Learning. Long Beach， USA： JMLR： 6105-6114 ［DOI： 10.48550/arXiv.1905.11946http://dx.doi.org/10.48550/arXiv.1905.11946］
Tan M X， Pang R M and Le Q V. 2020. EfficientDet： scalable and efficient object detection//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， USA： IEEE： 10778-10787 ［DOI： 10.1109/CVPR42600.2020.01079http://dx.doi.org/10.1109/CVPR42600.2020.01079］
Taniguchi K， Ueta K， Onishi H and Tatsumi S. 2007. A method of Mura intensity quantification using multi-level sliced images//Proceedings Volume 6356， the 8th International Conference on Quality Control by Artificial Vision. Le Creusot， France： SPIE： 124-131 ［DOI： 10.1117/12.736735http://dx.doi.org/10.1117/12.736735］
Torres G M， Souza A S， Ferreira D A O， Junior L C S G， Ouchi K Y， Valadao M D M， Silva M O， Cavalcante V L G， Mattos E V C U， Pereira A M C， Cruz C F S， Silva A P， Belem R J S， Costa A S， Evangelista L G C， Junior W C C， Paula R G， Bezerra T B， Junior W S S and Carvalho C B. 2021. Automated Mura defect detection system on LCD displays using random forest classifier//Proceedings of 2021 IEEE International Conference on Consumer Electronics （ICCE）. Las Vegas， USA： IEEE： #9427579 ［DOI： 10.1109/ICCE50685.2021.9427579http://dx.doi.org/10.1109/ICCE50685.2021.9427579］
Tsai D M， Chuang S T and Tseng Y H. 2007. One-dimensional-based automatic defect inspection of multiple patterned TFT-LCD panels using Fourier image reconstruction. International Journal of Production Research， 45（6）： 1297-1321 ［DOI： 10.1080/00207540600622464http://dx.doi.org/10.1080/00207540600622464］
Tsai D M， Fan S K S and Chou Y H. 2021. Auto-annotated deep segmentation for surface defect detection. IEEE Transactions on Instrumentation and Measurement， 70： #5011410 ［DOI： 10.1109/TIM.2021.3087826http://dx.doi.org/10.1109/TIM.2021.3087826］
Tsai D M and Hung C Y. 2005. Automatic defect inspection of patterned thin film transistor-liquid crystal display （TFT-LCD） panels using one-dimensional Fourier reconstruction and wavelet decomposition. International Journal of Production Research， 43（21）： 4589-4607 ［DOI： 10.1080/00207540500140732http://dx.doi.org/10.1080/00207540500140732］
Tsai D M， Lin P C and Lu C J. 2006. An independent component analysis-based filter design for defect detection in low-contrast surface images. Pattern Recognition， 39（9）： 1679-1694 ［DOI： 10.1016/j.patcog.2006.03.005http://dx.doi.org/10.1016/j.patcog.2006.03.005］
Tuyen Le N， Wang J W， Shih M H and Wang C C. 2020. Novel framework for optical film defect detection and classification. IEEE Access， 8： 60964-60978 ［DOI： 10.1109/ACCESS.2020.2982250http://dx.doi.org/10.1109/ACCESS.2020.2982250］
Wang H S and Yang Y Y. 2018. Surface defect inspection of TFT-LCD panels based on improved saliency model. Journal of Electronic Measurement and Instrumentation， 32（7）： 29-35
王宏硕， 杨永跃. 2018. 基于改进显著性模型的TFT-LCD面板缺陷检测. 电子测量与仪器学报， 32（7）： 29-35 ［DOI： 10.13382/j.jemi.2018.07.005http://dx.doi.org/10.13382/j.jemi.2018.07.005］
Wang X， Dong R and Li B. 2016. TFT-LCD Mura defect detection based on ICA and multi-channels fusion//Proceedings of the 3rd International Conference on Information Science and Control Engineering （ICISCE）. Beijing， China： IEEE： 687-691 ［DOI： 10.1109/ICISCE.2016.152http://dx.doi.org/10.1109/ICISCE.2016.152］
Wang Y Y， Hou J， Li M S， Xue T and Xiao X. 2021. Defect detection of LCD based on texture elimination. Electronic Measurement Technology， 44（12）： 93-96
汪永勇， 侯俊， 李梦思， 薛彤， 肖雄. 2021. 基于纹理消除的液晶屏缺陷检测. 电子测量技术， 44（12）： 93-96 ［DOI： 10.19651/j.cnki.emt.2106557http://dx.doi.org/10.19651/j.cnki.emt.2106557］
Wieler M， Hahn T and Hamprecht F A. 2007. Weakly supervised learning for industrial optical inspection ［EB/OL］. ［2023-07-06］. https://hci.iwr.uni-heidelberg.de/content/weakly-supervised-learning-industrial-optical-inspectionhttps://hci.iwr.uni-heidelberg.de/content/weakly-supervised-learning-industrial-optical-inspection
Xie E Z， Wang W J， Wang W H， Sun P Z， Xu H， Liang D and Luo P. 2021. Trans2Seg： transparent object segmentation with Transformer ［EB/OL］. ［2023-07-06］. https://arxiv.org/pdf/2101.08461v2.pdfhttps://arxiv.org/pdf/2101.08461v2.pdf
Xie R， Li G and Zhang R B. 2016. High quality background modeling of LCD-Mura defect. Journal of Computer Applications， 36（4）： 1151-1155， 1162
谢瑞， 李钢， 张仁斌. 2016. 液晶显示器斑痕缺陷高质量背景建模. 计算机应用， 36（4）： 1151-1155 ［DOI： 10.11772/j.issn.1001-9081.2016.04.1151http://dx.doi.org/10.11772/j.issn.1001-9081.2016.04.1151］
Xie X H and Mirmehdi M. 2007. TEXEMS： texture exemplars for defect detection on random textured surfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence， 29（8）： 1454-1464 ［DOI： 10.1109/TPAMI.2007.1038http://dx.doi.org/10.1109/TPAMI.2007.1038］
Yan C C， Jin S Q， Yan Z Z and Hu H B. 2017. TFT-LCD detection algorithm combining weighted template difference image and bilateral filtering. Journal of Electronic Measurement and Instrumentation， 31（9）： 1434-1440
严成宸， 金施群， 闫真真， 胡海兵. 2017. 结合加权模板差图与双边滤波的TFT-LCD检测算法. 电子测量与仪器学报， 31（9）： 1434-1440 ［DOI： 10.13382/j.jemi.2017.09.013http://dx.doi.org/10.13382/j.jemi.2017.09.013］
Yang H， Chen Y F， Song K Y and Yin Z P. 2019. Multiscale feature-clustering-based fully convolutional autoencoder for fast accurate visual inspection of texture surface defects. IEEE Transactions on Automation Science and Engineering， 16（3）： 1450-1467 ［DOI： 10.1109/TASE.2018.2886031http://dx.doi.org/10.1109/TASE.2018.2886031］
Yang H， Mei S， Song K Y， Tao B and Yin Z P. 2018b. Transfer-learning-based online Mura defect classification. IEEE Transactions on Semiconductor Manufacturing， 31（1）： 116-123 ［DOI： 10.1109/TSM.2017.2777499http://dx.doi.org/10.1109/TSM.2017.2777499］
Yang H， Song K Y， Mei S and Yin Z P. 2018a. An accurate Mura defect vision inspection method using outlier-prejudging-based image background construction and region-gradient-based level set. IEEE Transactions on Automation Science and Engineering， 15（4）： 1704-1721 ［DOI： 10.1109/TASE.2018.2823709http://dx.doi.org/10.1109/TASE.2018.2823709］
Yang H， Zhou Q Y， Song K Y and Yin Z P. 2021. An anomaly feature-editing-based adversarial network for texture defect visual inspection. IEEE Transactions on Industrial Informatics， 17（3）： 2220-2230 ［DOI： 10.1109/TII.2020.3015765http://dx.doi.org/10.1109/TII.2020.3015765］
Yang Q， Zhao Y Q， Zhang F and Liao M. 2022. Automatic segmentation of defect in high-precision and small-field TFT-LCD images. Laser and Optoelectronics Progress， 59（12）： 1215008
杨勍， 赵于前， 张帆， 廖苗. 2022. 高精度小视野TFT-LCD图像异物缺陷自动分割. 激光与光电子学进展， 59（12）： #1215008 ［DOI： 10.3788/LOP202259.1215008http://dx.doi.org/10.3788/LOP202259.1215008］
Yun J W， Gu H， Kim D H， Moon H S and Ko S J. 2014. Automatic Mura inspection using the principal component analysis for the TFT-LCD panel//Proceedings of 2014 IEEE International Conference on Consumer Electronics. Taipei， China： IEEE： 109-110 ［DOI： 10.1109/ICCE-TW.2014.6904008http://dx.doi.org/10.1109/ICCE-TW.2014.6904008］
Zeng Y. 2017. Research of Key Technologies for TFT-LCD Display Defects Detection System Base on Machine Vision. Yueyang： Hunan Institute of Science and Technology
曾毅. 2017. 基于机器视觉的液晶屏点灯缺陷检测系统关键技术研究. 岳阳： 湖南理工学院
Zhang T D， Lu R S and Zhang S Z. 2016. Surface defect inspection of TFT-LCD panels based on 2D DFT. Opto-Electronic Engineering， 43（3）： 7-15
张腾达， 卢荣胜， 张书真. 2016. 基于二维DFT的TFT-LCD平板表面缺陷检测. 光电工程， 43（3）： 7-15 ［DOI： 10.3969/j.issn.1003-501X.2016.03.002http://dx.doi.org/10.3969/j.issn.1003-501X.2016.03.002］
Zhang Y and Zhang J. 2006a. Automatic blemish inspection for TFT-LCD based on polynomial surface fitting. Opto-Electronic Engineering， 33（10）： 108-114
张昱， 张健. 2006a. 基于多项式曲面拟合的TFT-LCD斑痕缺陷自动检测技术. 光电工程， 33（10）： 108-114 ［DOI： 10.3969/j.issn.1003-501X.2006.10.021http://dx.doi.org/10.3969/j.issn.1003-501X.2006.10.021］
Zhang Y and Zhang J. 2006b. Application of fuzzy expert system in defect inspection of TFT-LCD. Journal of Optoelectronics·Laser， 17（6）： 719-723
张昱， 张健. 2006b. 模糊专家系统在TFT-LCD缺陷检测中的应用. 光电子·激光， 17（6）： 719-723 ［DOI： 10.3321/j.issn：1005-0086.2006.06.018http://dx.doi.org/10.3321/j.issn：1005-0086.2006.06.018］
Zhou Z H. 2016. Machine Learning. Beijing： Tsinghua University Press
周志华. 2016. 机器学习. 北京： 清华大学出版社
Zhu H D， Huang J C， Liu H W， Zhou Q W， Zhu J Q and Li B Q. 2022. Deep-learning-enabled automatic optical inspection for module-level defects in LCD. IEEE Internet of Things Journal， 9（2）： 1122-1135 ［DOI： 10.1109/JIOT.2021.3079440http://dx.doi.org/10.1109/JIOT.2021.3079440］
相关文章
相关作者
相关机构
京公网安备11010802024621