臺灣博碩士論文加值系統

　　隨著現代科技的不斷進步，具有輕、薄、省電及高解析度等優點的平面顯示器(Flat Panel Display, FPD)，已經逐漸地取代傳統的陰極映像管(Cathode Ray Tube, CRT)。由於近幾年平面顯示產品中，只有LCD的技術和生產線較為成熟，其中以薄膜電晶體液晶顯示器(TFT-LCD)為目前市場主流，而在現階段TFT-LCD的生產中，彩色濾光片可說是所有生產材料中最重要的關鍵材料。因此，正確地檢測出彩色濾光片的瑕疵並做好分類，將可使製
程工程師更容易找出造成瑕疵的原因並改善，同時避免因為彩色濾光片之瑕疵未檢測出來而繼續製造，導致後續製程材料的浪費，增加廠商的成本負擔。TFT-LCD中彩色濾光片的瑕疵，可分為微觀瑕疵(micro defect)和巨觀瑕疵(macro defect)兩大類，微觀瑕疵主要是指較小區域或是較不明顯的瑕疵，巨觀瑕疵則是指較大區域或
是較明顯的瑕疵。而本研究主要是以類神經網路模式中的自適應共振理論網路為基礎，針對彩色濾光片表面的微觀瑕疵建構辨識系統，以求能正確且快速地分類微觀瑕疵，輔助技術人員進行檢測，並改善人工目視檢查的缺點。

摘要 i
誌謝 ii
表目錄 v
圖目錄
vii

第一章 緒論 1
1.1 研究動機 ............................................................ 2
1.2 研究目的 ............................................................ 3
1.3 研究範圍與限制 ...................................................... 4
1.4 論文架構 ............................................................ 5

第二章 相關文獻回顧 6
2.1 彩色濾光片之介紹 .................................................... 6
2.1.1 基本構成 ...................................................... 7
2.1.2 製造方法 ...................................................... 9
2.1.3 瑕疵檢測 ...................................................... 9
2.2 數位影像處理 ....................................................... 12
2.2.1 影像相減 ..................................................... 14
2.2.2 影像遮罩 ..................................................... 14
2.3 類神經網路模式應用 .................................................. 15
2.3.1 自適應共振理論網路 ........................................... 16
2.3.2 ART2 ......................................................... 19
2.3.3 Fuzzy ART .................................................... 22
2.3.4 半導體瑕疵檢測之應用 ......................................... 24
2.4 基因演算法 ......................................................... 25

第三章 問題定義與模式 28
3.1 問題描述與基本假設 ................................................. 28
3.1.1 問題描述 ..................................................... 29
3.1.2 基本假設 ..................................................... 31
3.1.3 符號說明 ..................................................... 32
3.2 微觀瑕疵辨識系統之模式建立 ......................................... 34
3.2.1 影像相減 ..................................................... 34
3.2.2 微觀瑕疵之特徵值 ............................................. 34
3.2.3 類神經網路模式 ............................................... 38
3.2.4 基因演算法 ................................................... 43
3.2.5 小結 ......................................................... 47

第四章 模擬試驗 49
4.1 微觀瑕疵產生器暨模擬資料 ........................................... 49
4.2 微觀瑕疵辨識系統之測試驗證 ......................................... 54
4.2.1 模擬微觀瑕疵種類個數之分析 ................................... 58
4.2.2 Fuzzy ART於微觀瑕疵特徵個數之分析 ............................ 61
4.3 小結 ............................................................... 65

第五章 結論與未來研究方向 67
5.1 結論 ............................................................... 67
5.2 未來研究方向 ....................................................... 68

參考文獻 70

楊明仁. 台灣TFT-LCD彩色濾光片產業發展概況. 台灣工業銀行產業研究分析報告, 2002.

楊明仁. TFT-LCD 次世代生產線發展概況. 台灣工業銀行產業研究分析報告, 2003.

葉怡成. 類神經網路模式應用與實作(8 ed.). 儒林圖書有限公司, 2003.

卓聖鵬. 彩色液晶顯示器(1 ed.). 全華科技圖書股份有限公司, 2001.

Baraldi, A. and Blonda, P. A survey of fuzzy clustering algorithms for pattern recognition. II. Systems, Man and Cybernetics, Part B, IEEE Transactions on, 29(6),786-801, 1999.

Carpenter, G. A. and Grossberg, S. A massively parallel architecture for a self-organizing neural pattern recognition machine. Computer Vision, Graphics, and Image Processing, 37(1), 54-115, 1987a.

Carpenter, G. A. and Grossberg, S. ART 2: Self-organization of stable category recognition codes for analog input patterns. Applied Optics, 26(23), 4919-4930, 1987b.

Carpenter, G. A. and Grossberg, S. ART 3: Hierarchical search using chemical transmitters in self-organizing pattern recognition architectures. Neural Networks, 3, 129-152, 1990.

Carpenter, G. A., Grossberg, S. and Reynolds, J. H. ARTMAP: Supervised real-
time learning and classi‾cation of nonstationary data by a self-organizing neural network. Neural Networks, 4, 565-588, 1991.

Carpenter, G. A., Grossberg, S. and Rosen, D. B. ART 2-A: An adaptive resonance
algorithm for rapid category learning and recognition. Neural Networks, 4, 493-504, 1991a.

Carpenter, G. A., Grossberg, S. and Rosen, D. B. Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks, 4, 759-771, 1991b.

Chen, F.-L. and Liu, S.-F. A neural-network approach to recognize defect spatial pattern in semiconductor fabrication. IEEE Transactions on Semiconductor Manufacturing, 13(3), 366-373, 2000.

Chen, S.-F. and Liu, Y.-J. An adaptive genetic assembly-sequence planner. International Journal of Computer Integrated Manufacturing, 14(5), 489-500, 2001.

Credelle, T. L. 1988. Thin-‾lm transistors for video applications. In Display Research Conference, 1988., Conference Record of the 1988 International (pp. 208-214). San Diego, CA.

Dayhoff, J. E. Neural network architectures: An introduction. Van Nostrand Reinhold, 1990.

Frank, T., Kraiss, K.-F. and Kuhlen, T. Comparative analysis of fuzzy ART and ART-2A network clustering performance. Neural Networks, IEEE Transactions on,
9(3), 544-559, 1998.

Freeman, J. A. and Skapura, D. M. Neural Networks: Algorithms, Applications, and Programming Techniques. Addison-Wesley, 1992.

Gen, M. and Cheng, R. Genetic Algorithms and Engineering Design. John Wiley &
Sons, Inc., 1996.

Gonzalez, R. C. and Woods, R. E. Digital Image Processing (2 ed.). Prentice Hall, 2002.

Grossberg, S. Adaptive pattern-classi‾cation and universal recoding: I. Parallel development and coding of neural feature detectors. Biological Cybernetics, 23(3), 121-134, 1976a.

Grossberg, S. Adaptive pattern-classi‾cation and universal recoding: II. Feedback, expectation, olfaction, illusions. Biological Cybernetics, 23(4), 187-202, 1976b.

Jang, J., Lim, S. and Oh, M. Technology development and production of flat panel displays in Korea. Proceedings of the IEEE, 90(4), 501-513, 2002.

Kim, J.-H., Ahn, S., Jeon, J. W. and Byun, J.-E. 2001. A high-speed high-resolution vision system for the inspection of TFT LCD. In Industrial Electronics, 2001. Proceedings. ISIE 2001. IEEE International Symposium on (Vol. 1, pp. 101-105). Pusan.

Lalama, S. J. 1994. Flat panel display manufacturing overview. In Electronics Manufacturing Technology Symposium, 1994. 'Low-Cost Manufacturing Technologies
for Tomorrow's Global Economy'. Proceedings 1994 IEMT Symposium., Sixteenth
IEEE/CPMT International (Vol. 1, pp. 185{190). La Jolla, CA.

Lee, E. W. M., Lim, C. P., Yuen, R. K. K. and Lo, S. M. A hybrid neural network
model for noisy data regression. Systems, Man and Cybernetics, Part B, IEEE
Transactions on, 34(2), 951-960, 2004.

Man, K. F., Tang, K. S. and Kwong, S. Genetic Algorithms: Concepts and Designs.
Springer, 1999.

Mentley, D. E. State of °at-panel display technology and future trends. Proceedings of the IEEE, 90(4), 453-459, 2002.

Morimoto, M. 1994. Trends of marketing and technology in TFT{LCD. In Elec-
tronics Manufacturing Technology Symposium, 1994. 'Low-Cost Manufacturing
Technologies for Tomorrow's Global Economy'. Proceedings 1994 IEMT Sympo-
sium., Sixteenth IEEE/CPMT International (Vol. 1, pp. 384-386). La Jolla,
CA.

Morris, J. R. 1995. Interconnection and assembly of LCDs. In Active Matrix Liquid Crystal Displays, 1995. AMLCDs '95., Second International Workshop on (pp. 66-71). Bethlehem, PA.

Muraoka, T., Sakai, N. and Tsuchiya, T. 1996. Automatic discrimination system
for color unevenness in the picture on thin film transistor type of liquid crystal display adapted to the color sensation of dark eyes. In Industrial Electronics, Control, and Instrumentation, 1996., Proceedings of the 1996 IEEE IECON 22nd International Conference on (Vol. 3, pp. 1434-1440). Taipei.

Nakashima, K. 1994. Hybrid inspection system for LCD color filter panels. In Instrumentation and Measurement Technology Conference, 1994. IMTC/94. Con-ference Proceedings. 10th Anniversary. Advanced Technologies in I and M., 1994
IEEE (Vol. 2, pp. 689-692). Hamamatsu.

Sabnis, R. W. Color filter technology for liquid crystal displays. Displays, 20, 119-129, 1999.

Shen, G.-S. 2002. LCD driver IC assembly technologies and status. In Electronic
Materials and Packaging, 2002. Proceedings of the 4th International Symposium
on (pp. 313-316). KaoShiung, Taiwan.

Smith, G. C. and S.-F., S. S. An enhanced genetic algorithm for automated assembly planning. Robotics and Computer Integrated Manufacturing, 18, 355-364, 2002.

Su, C.-T., Yang, T. and Ke, C.-M. A neural-network approach for semiconductor wafer post-sawing inspection. IEEE Transactions on Semiconductor Manufacturing,
15(2), 260-266, 2002.

Whiteley, J. R., Davis, J. F., Mehrotra, A. and Ahalt, S. C. Observations and problems applying ART2 for dynamic sensor pattern interpretation. Systems, Man and Cybernetics, Part A, IEEE Transactions on, 26(4), 423-437, 1996.