臺灣博碩士論文加值系統

顯示器（Display）是資訊時代人們訊息傳遞與溝通之重要界面，平面顯示器（Flat-panel displays）具有小至輕薄可攜性與大至應用於公眾公佈欄領域之特性，更加帶給人們許多生活上之便利。本研究針對薄膜電晶體液晶顯示面板(TFT-LCD)提出以獨立成分分析為基(ICA-based)之方法，分別應用於一維時間序列訊號的製程監控與二維影像之Mura瑕疵檢測。透過對關鍵製程參數的監測能夠於製程中即時有效的提升良率與避免材料的浪費。本研究導入獨立成分分析於TFT面板之製程參數變異偵測，偵測對象選定為總斜度變異量，總斜度變異量是一個關鍵監控參數，目的為觀測對組工程中的變異量，該變異量會形成如對組位移造成顯示畫面不均勻的斑或漏光之現象，透過總斜度變異量的監控可以有效且快速回饋製程變異，避免大量不良品的產生。本研究透過ICA分別出製程參數資料之獨立成分，針對獨立成分資訊即可分辨出製程變異。相較於目前TFT-LCD的製程變異偵測採用之傳統的統計管制圖，可獲得良好之變異偵測結果。經實驗與真實資驗證本研究採用之ICA方法對TFT面板變異量監控具有良好效果。

針對Mura影像以機器視覺方法進行瑕疵檢測。Mura瑕疵在顯示器面板上呈現光源不均現象，並且與周圍背景具低對比度相似不易偵測特徵。本研究提出一個以獨立成分分析為基(ICA-based)之Mura瑕疵檢測方法，分為二階段：訓練階段透過無瑕疵樣本建立基影像與特徵向量，基影像間同時具有統計獨立與空間不重複之特性，其中目標式結合了統計獨立的最大負熵與空間不重複性的最小相關係數，無瑕疵樣本則為基影像與特徵向量之線性組合；測試階段針對測試之影像利用訓練之特徵向量與測試影像之特徵向量距離辨別是否為瑕疵影像。實驗結果顯示訓練之基影像可以充分代表LCD 無瑕疵影像具有源不均的之組成，亦使得特徵向量可有效的於測試階段將瑕疵與無瑕疵影像分辨出來。本論文所提出之方法具有良好之計算效率，十分適於即時之線上檢測。

In this dissertation, two ICA-based approaches have been proposed for process monitoring of 1-D time-series data and mura detection of 2-D images in TFT-LCD manufacturing. For 1-D signal process monitoring and control, independent components (ICs) are used as source signals for statistical process control. To improve the yield of Liquid Crystal Display (LCD) panels, process control becomes a critical task in LCD manufacturing. In this study, a control chart based on Independent Component Analysis (ICA) is proposed to monitor TFT-LCD process variation. The proposed method can be effectively used in the monitoring of LCD critical process parameter, called Total Pitch (TP). TP is a parameter that is used to control alignment errors in TFT-LCD process. TP variations will cause serious defects like mura (brightness unevenness of a panel) and small bright points on the display area of LCD panels. Since the collected data could be a mixture of noise and different source signals, ICA is first applied to separate mixed data into independent components. The X-bar and R control charts are then used to monitor the separated source signals. Experimental results on real measured data of TP in the TFT-LCD process show that the proposed method can reliably detect process variations.

For mura inspection in 2-D images, a machine vision approach is proposed for detecting local irregular brightness in low-contrast surface images and, especially, with focus on Mura defects in LCD panels. A Mura defect embedded in a low-contrast surface image shows no distinct intensity from its surrounding region, and the sensed image may also present uneven illumination on the surface. All these make the Mura defect detection in low-contrast surface images extremely difficult. A set of basis images derived from defect-free surface images are used to represent the general appearance of a clear surface. Each LCD image is then constructed as a linear combination of the basis images, and the coefficients of the combination form the feature vector for discriminating Mura defects from clear surfaces. In order to find minimum number of basis images for efficient and effective representation, the basis images are designed such that they are both statistically independent and spatially exclusive. An ICA-based model that finds both the maximum negentropy for statistical independence and minimum spatial correlation for spatial redundancy is proposed to extract the representative basis images. Experimental results have shown that the proposed method can effectively detect various Mura defects in low-contrast LCD panel images. It is also computationally very fast for real-time, on-line inspection.

摘要 I
Abstract II
誌謝 III
Table of Contents IV
List of Figures VI
List of Tables VII

1. Introduction 1
1.1 Motivation 1
1.2 Main contributions 3
1.3 Organization of the dissertation 4

2. LCD Manufacturing Process and Literature Review 5
2.1 Overview of the TFT-LCD process 5
2.1.1 Array process 10
2.1.2 Cell process 11
2.1.3 Module process 14
2.2 ICA in Statistical Process Control (SPC) 15
2.3 Defect detection in TFT-LCD panels 18
2.4 ICA in computer vision application 22

3. ICA-based detection for Total Pitch (TP) variations in TFT-LCD Process 25
3.1 Overview of ICA 25
3.1. Measures of independence 27
3.1.1 High order cumulants 27
3.1.2 Negentropy 28
3.1.3 Mutual information 30
3.2 Total pitch in TFT-LCD Process Monitoring 33
3.3 The properties ICA-based method for process monitoring in TP data 36
3.4 Experimental results 37
3.5 Summary 38

4. Basis image reconstruction for defect detection 42
4.1 Overview of LCD surfaces images 42
4.2 Representative basis images 45
4.3 Statistically and spatially independent model 49
4.4 The PSO procedure 53
4.5 Experiments results 62
4.5.1 Detection results 62
4.5.2 Effect of the number of basis images 69
4.6 Summary 76

5. Conclusions 77
References 78

Amari, A., Cichocki, A., Yang, H., 1996, A new learning algorithm for blind source separation, In: Advances in Neural Information Processing Systems, D. Touretzky, M. Mozer, M. Hasselmo (Eds.), MIT Press, Cambridge, MA, pp. 757-763.
Beckmann, C. F., Smith, S. M., 2004, Probabilistic independent component analysis for functional magnetic resonance imaging, IEEE Trans. Medical Imaging, 23, pp. 137-152.
Bell, A. J., Sejnowski, T. J., 1995, An information-maximization approach to blind separation and blind deconvolution, Neural Computation, 7, pp. 1129-1159.
Borror, C., Montgomery, D., Runger, G., 1999, Robustness of the EWMA control charts to non-normality, Journal of Quality Technology, 313, pp. 309–316.
Borror, C., Champ, C., Rigdon, S., 1998, EWMA control charts for Poisson data, Journal of Quality Technology, 30, pp. 352–361.
Brzakovic, D., Vujovic, N., 1996, Designing defect classification system: a case study, Pattern Recognition, 29, pp. 1401-1419.
Chen, H.-C., Fang, L.-T., Lee, L., 2005, LOG filter based inspection of cluster Mura and vertical-band Mura on liquid crystal displays. In: Proceedings of SPIE-IS&T Electronic Image, 5679, pp. 257-265.
Chen, Y. W., Zeng, X. Y., Lu, H., 2002, Edge detection and texture segmentation based on independent component analysis, Proceedings of the 16th International Conference on Pattern Recognition, Quebec City, Canada, pp. 351-354.
Clerc, M., Kennedy, J., 2002, The particle swarm-explosion, stability and convergence in a multidimensional complex space, IEEE Trans. Evol. Comput., 6, pp. 58-73.
Cover, T. M. and J. A. Thomas, 1991, Elements of Information Theory, John Wiley and Sons, New York, NY.
Crowder, S. A., 1987, Simple method for studying run-length distribution of exponentially weighted moving average charts, Technometrics, 29, pp. 401–407.
Crowder, S. A., 1989, Design of exponentially weighted moving average schemes, Journal of Quality Technology, 21, pp. 155–162.
Cristaldi, D. J. R., Pennisi F., Pulvirenti, F., 2009, Liquid Crystal Display Drivers: Techniques and Circuits, Springer, NY, pp. 15
Deville, Y., Andry, L., 1996, Application of blind source separation techniques to multi-tag contactless identification systems, IEICE Trans. Fundamentals of Electronics, Communications and Computer Sciences E79-A, pp. 1694-1699.
Fernandez, C., Platero, D., Campoy, P., Aracil, R., 1993, Vision system for on-line surface inspection in aluminum casting process, In: Proceedings of the IEEE International Conference on Industrial Electronics, Control, Instrumentation and Automation (IECON’93), pp. 1854-1859.
Gelle, G., Colas, M., Serviere, C., 2001, Blind source separation: a tool for rotating machine monitoring by vibrations analysis, J Sound Vibration, 248, pp. 865-85.
Harris, T.J., Ross, W.H., 1991, Statistical process control procedures for correlated observations, The Canadian Journal of Chemical Engineering, 69, pp. 48-57.
Hoyer, P. O., 2004, Non-negative matrix factorization with sparseness constraints, Journal of Machine Learning Research, 5, pp. 1457-1469.
Hunter, J., 1986, The exponential weighted moving average, Journal of Quality Technology, 18, pp. 203-209.
Hurri, J., Gävert, H., Särelä, J., Hyvärinen, A., 2004, FastICA Package, Online Available: http://www.cis.hut.fi/projects/ica/fastica/.
Hyvärinen, A., Karhunen, J., Oja, E., 2001, Independent Component Analysis, John Wiley & Sons, New York.
Hyvärinen, A., Oja, E., 2000, Independent component analysis: algorithms and applications, Neural Computation, 13, pp. 411-430.
Hyvarinen, A., Oja, E., 1997, A fast fixed-point algorithm for independent component analysis, Neural Computation, 9, pp.1483-1492.
Hyvarinen, A., 1999, Fast and robust fixed-point algorithms for independent component analysis, IEEE Trans. Neural Networks 10, pp. 626-634
Jenssen, R., Eltoft, T., 2003, Independent component analysis for texture segmentation, Pattern Recognition, 36, pp. 2301-2315.
Jiang, B. C., Wang, C.-C., Liu, H.-C., 2005, Liquid crystal display surface uniformity defect inspection using analysis of variance and exponentially weighted moving average techniques, International Journal of Production Research, 43, pp. 67-80.
Kano, M., Tanaka, S., Hasebe, S., Hashimoto, I. and Ohno, H., 2003, Monitoring of independent components for fault detection, AIChE Journal, 49, pp. 969-976.
Katayama, M., 1999, TFT-LCD technology, Thin Solid Films, 341, pp. 140-147.
Kennedy, J., Eberhart, R., 1995, Particle swarm optimization, In: Proceedings of the IEEE International Conference on Neural Networks, Perth, Australia, pp. 1942-1948.
Kennedy, J., 1997, The particle swarm: social adaptation of knowledge, In: Proceedings of the IEEE International Conference on Evolutionary Computation, Piscataway, NJ, pp. 303-308.
Kim, W.-S., Kwak, D.-M., Song, Y.-C, Choi, D.-H., Park, K.-H., 2004, Detection of spot-type defects on liquid crystal display modules, Key Engineering Materials, 270-273, pp. 808-813.
Koo, H. S., 2004, Fundamentals and Applications of Optoelectronic Liquid Crystal Display Technology, Gao-Lin Book Publications Ltd., Taipei, ROC.
Lalama, S. J., 1994, Flat panel display manufacturing overview, In: Proceedings 1994 IEEE Electronics Manufacturing Technology Symposium, La Jolla, CA, USA, pp. 185-190.
Lee, D. D., Seung, H. S., 1999, Learing the parts of object by non-negative matrix factorization, Nature 401, pp. 788-91.
Lee, J. M., Yoo, C., Lee, I. B., 2003, On-line batch process monitoring using different unfolding method and independent component analysis, Journal of Chem Eng Japan, 36, pp. 1384-1396.
Lee, J. Y., Yoo, S. I., 2004, Automatic detection of region-Mura defect in TFT-LCD, IEICE Trans. Inf. and Syst. E87-D, pp. 2371-2378.
Lee, T. W., 1998, Independent Component Analysis: Theory and Application, Kluwer Academic Publishers, Boston, MA.
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, pp. 136-147.
Li, W. Gu, F., Ball, A. D., Leung, A. Y. T., Phipps, E., 2001, A study of the noise from diesel engines using the independent component analysis, Mech Syst Signal Process, 15, pp. 1165-1184.
Li, S. Z., Hou, X. W., Zhang, H. J., 2001, Learning spatially localized, parts-based representation, Computer Vision and Pattern Recognition, 1, pp. 207-212.
Lucas, J., Saccucci, M., 1990, Exponentially weighted moving average control schemes: Properties and enhancements, Technometrics, 32, pp. 1-12.
MacGregor, J., Harris, T., 1993, The exponentially weighted moving variance, Journal of Quality Technology, 251, pp. 106-118.
Manduchi, R., Portilla, J., 1999, Independent component analysis of textures, Proceedings of the IEEE International Conference on Computer Vision, Kerkyra, Greece, pp. 1054-1060.
Montegomery, D. C., 1985, Introduction to Statistical Quality Control, Wiley, New York.
Montegomery, D.C. and Mastrangelo, C.M., 1991, Some statistical process control methods for auto-correlated data, Journal of Quality Technology, 23, pp. 179-193.
Nomikos, P., MacGregor, J. F., 1994, Monitoring batch processes using multi-way principal component analysis, AIChE Journal, 40, 1361-1375.
Olshausen, B. A., Field, D. J., 1996, Emergence of simple-cell receptive field properties by learning a sparse code for natural images, Nature, 381, pp. 607-609
Olsson, J., Gruber, S., 1992, Web process inspection using neural classification of scattering light, In: Proceedings of the IEEE International Conference on Industrial Electronics, Control, Instrumentation and Automation (IECON’92), pp. 1443-1448.
Oh, J.-H., Kwak, D.-M., Lee, K.-B., Song, Y.-C., Choi, D.-H., Park, K.-H., 2004, Line defect detection in TFT-LCD using directional filter bank and adaptive multilevel thresholding, Key Engineering Materials, 270-273, pp.233-238
Papoulis, A., 1991, Probability, Random Variables and Stochastic Processes, Mc-Graw-Hill, Inc., New York, NY, USA.
Park, H. M., Jung, H. Y., Lee, T. W., Lee, S. Y., 1999, On subband-based blind signal separation for noisy speech recognition, Electronic Letters, 35, pp. 2011-2012.
Penev, P., Atick, J., 1996, Local feature analysis: a general statistical theory for object representation, Natwork: Computation in Neural Systems, 7, pp. 477-500.
Ramana, K. V., Ramamoorthy, B., 1996, Statistical methods to compare the texture features of machine surfaces, Pattern Recognition, 29, pp. 1447-1459
Roberts, S., 1959, Control chart tests based on geometric moving averages, Technometrics, 1, pp. 239–250.
Ryu, J.-S., Oh, J.-H., Kim, J.-G., Koo, T.-M., Park, K.-H., 2004, TFT-LCD panel blob-Mura inspection using the correlation of wavelet coefficients. In: TENCON 2004 (2004 IEEE Region 10 Conference), Chiang Mai, Thailand, pp. 219-222.
Saitoh F.,1999, Boundary extraction of brightness unevenness on LCD display using genetic algorithm based on perceptive grouping factors, Proceedings of the International Conference on Image Processing, Kobe, Japan, pp. 308-312.
Serdaroglu, S., Ertuzun, A., 2006, A. Ercil, Defect detection in textile fabric images using wavelet transforms and independent component analysis, Pattern Recognition and Image Analysis, 16, pp. 61-64.
Serdaroglu, S., Ertuzun, A., Ercil, A., 2007, Defect detection in textile fabric images using subband domain subspace analysis, Pattern Recognition and Image Analysis, 17, pp. 663-674.
Sezer, O. G., Ercil, A., Ertuzun, A., 2007, Using perceptual relation of regularity and anisotropy in the texture with independent component model for defect detection, Pattern Recognition, 40, pp. 121-133.
Sokolov, S. M., Treskunov, A. S., 1992, Automatic vision system for final test of liquid crystal display, In: Proceedings of the IEEE International Conference on Robotics and Automation, Nice, France, pp. 1578-1582.
Shi, Y., Eberhart, R., 1998, A modified particle swarm optimizer, In: Proceedings of the IEEE International Conference on Evolutionary Computation, Anchorage, Alaska, pp. 69-73.
Taniguchi, K., Ueta, K. and Tatsumi, S., 2006, A Mura detection method, Pattern Recognition, 39, pp. 1044-1052.
Tsai, D.-M., Lin, P.-C., Lu, C.-J., 2006, An independent component analysis-based filter design for defect detection in low-contrast surface images. Pattern Recognition, 39, pp. 1679-1694.
Tseng, Y.H. and Tsai, D.M., 2005, Using Independent Component Analysis for Process Monitoring in TFT-LCD Manufacturing, In: The 3rd ANQ Congress & The 19th Asia Quality Symposium, September 20-23, Taipei, Taiwan.
Thornhill, N. F., Shah, S. L., Huang, Vishnubhotla, B., 2002, A. Spectral principal component analysis of dynamic process data, Control Engineering Practice, 10, pp. 833-846.
Varney, J., 1992, Liquid crystal display assembly, Solid State Technology, 2, pp. 61-62.
Vigario, R., Sarela, J., Jousmaki, V., Hamalainen, M., Oja, E., 2000, Independent component approach to the analysis of EEG and MEG recordings, IEEE Trans. Biomedical Engineering, 47, pp. 589-593.
Wang, Z. and Ma, L., 2006, Implementation of region-Mura detection based on recursive polynomial-surface fitting algorithm. In: Second Asia International Symposium on Mechatronics (AISM 2006), Hong Kong.
Wilder, J., 1989, Finding and evaluating defects in glass, In: Machine Vision for Inspection and Measurement, H. Freeman (Ed.), Academic Press, New York, NY, 1, pp. 237.
Wold, S., Kettaneh, N., Friden, H., Holmberg, A., 1998, Modelling and diagnosis of batch processes and analogous kinetics experiments, Chemometrics and Intelligent Lab. Sys., 44, pp. 331-340.
Wright, J., A. Yang, Y., Ganesh, A., Sastry, S. S., Ma, Y., 2009, Robust face recognition via sparse representation, IEEE Trans. Pattern Analysis Mach. Intell, 31, pp. 210-227.
Wu, I. W., 1994, High-definition displays and technology trends in TFT-LCDs, Journal of Society for Information Display, 2, pp. 1-14.
Xia, C., Howell, J., 2003, Isolating multiple sources of plant-wide oscillations via independent component analysis, In: SAFEPROCESS2003 - 5th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes, Washinton, D.C., USA.
Xu, L., 1993, Least MSE reconstruction: a principle for self organizing nets, Neural Networks, 6, pp. 627-648.
Yao, Z. X., Qian, Y.; Li, X. X., Jiang, Y. B., 2003, A description of chemical processes based on state space, In Computer-Aided Chemical Engineering 15 - Proceedings of the 8th International Symposium on Process Systems Engineering, Chen, B., Westerberg, A. W., Eds.; Elsevier: Kunming, China, pp. 1112-1117
Zhang, Y., Zhang, J., 2005, Fuzzy recognition of the defect of TFT-LCD, In: Proceedings of SPIE, 5637, pp. 233-240.