A Hybrid Method of Frequency and Spatial Domain Techniques for TFT-LCD Circuits Defect Detection

被引:5
作者
Xia, Yan [1 ]
Luo, Chen [1 ]
Zhou, Yijun [1 ]
Jia, Lei [2 ]
机构
[1] Southeast Univ, Sch Mech Engn, Nanjing 211189, Peoples R China
[2] Wuxi Shangshi Elect Technol Co Ltd, Res & Dev Dept, Wuxi 214174, Jiangsu, Peoples R China
基金
中国国家自然科学基金;
关键词
Frequency-domain analysis; Feature extraction; Manganese; Image reconstruction; Thin film transistors; Inspection; Matched filters; Defect detection; frequency domain; spatial domain; TFT-LCD; template gmatching; NEURAL-NETWORK; INSPECTION; IMAGE; CLASSIFICATION; DESIGN;
D O I
10.1109/TSM.2022.3216289
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Defect detection is a crucial but challenging task in thin film transistor liquid crystal display (TFT-LCD) manufacturing. Existing vision-based methods focus on either spatial domain or frequency domain with unsatisfactory detection. In view of that, this paper proposes a hybrid template matching method by drawing benefits from both frequency and spatial domain techniques. Under proposal, frequency domain template matching method and saliency detector method are firstly adopted separately to obtain two candidate frequency components associated with defects. In template matching process, a novel selection criterion is taken to improve identifying components associated with local spatial anomaly. Subsequently, the inverse Fourier transform is applied on the intersection of the two candidates to reconstruct the defect regions. In final steps, image entropy in the spatial domain is employed to filter out false detection regions to improve accuracy. To meet industry's real-time inspection requirement, image partition and multi-threading calculation techniques are introduced into the proposed methodology. Experimental results have shown practical viability of the proposed approach to increase the yield rate of panels through robust defect detection in TFT-LCD manufacturing.
引用
收藏
页码:45 / 55
页数:11
相关论文
共 26 条
[1]   The Phase Only Transform for unsupervised surface defect detection [J].
Aiger, Dror ;
Talbot, Hugues .
2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2010, :295-302
[2]   Defect inspection for TFT-LCD images based on the low-rank matrix reconstruction [J].
Cen, Yi-Gang ;
Zhao, Rui-Zhen ;
Cen, Li-Hui ;
Cui, Li-Hong ;
Miao, Zhen-Jiang ;
Wei, Zhe .
NEUROCOMPUTING, 2015, 149 :1206-1215
[3]   Anisotropic diffusion with generalized diffusion coefficient function for defect detection in low-contrast surface images [J].
Chao, Shin-Min ;
Tsai, Du-Ming .
PATTERN RECOGNITION, 2010, 43 (05) :1917-1931
[4]   A Neural-Network Approach for Defect Recognition in TFT-LCD Photolithography Process [J].
Chen, Li-Fei ;
Su, Chao-Ton ;
Chen, Meng-Heng .
IEEE TRANSACTIONS ON ELECTRONICS PACKAGING MANUFACTURING, 2009, 32 (01) :1-8
[5]   Convolutional Neural Network for Wafer Surface Defect Classification and the Detection of Unknown Defect Class [J].
Cheon, Sejune ;
Lee, Hankang ;
Kim, Chang Ouk ;
Lee, Seok Hyung .
IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 2019, 32 (02) :163-170
[6]   Data-Driven Framework for Tool Health Monitoring and Maintenance Strategy for Smart Manufacturing [J].
Chien, Chen-Fu ;
Chen, Chia-Cheng .
IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 2020, 33 (04) :644-652
[7]  
Dougherty E. R., 2020, DIGITAL IMAGE PROCES
[8]  
Ge Z, 2021, Arxiv, DOI arXiv:2107.08430
[9]  
Hou Beiping, 2011, Chinese Journal of Scientific Instrument, V32, P2004
[10]   Microsoft COCO: Common Objects in Context [J].
Lin, Tsung-Yi ;
Maire, Michael ;
Belongie, Serge ;
Hays, James ;
Perona, Pietro ;
Ramanan, Deva ;
Dollar, Piotr ;
Zitnick, C. Lawrence .
COMPUTER VISION - ECCV 2014, PT V, 2014, 8693 :740-755