近年來半導體產業展現出高變動、高成長的特性，其中最常被討論的議題就是如何有效的提升良率，而高良率亦是製造業最重要的獲利指標，在半導體製造業中，晶圓缺陷不但是良率的最大阻礙，亦會造成製造成本的升高，因此晶圓缺陷的偵測與缺陷圖樣的辨識便成為晶圓廠內最重要的議題，發展出有效的辨識方法及系統更是改善良率不可或缺的要件，因此本研究同時採用多種的圖樣辨識手法，提出一能夠有效率的辨識晶圓缺陷圖樣的方法論，在研究中將晶圓缺陷圖樣概分為直線型、曲線型、環形、區域型、放射型、重複型及晶片邊緣型，除了這些單一缺陷圖樣問題外，本研究亦提出多重缺陷圖樣問題的解決方法，以期此方法論能夠更切合實際應用領域，研究中定義出五種不同的多重圖樣關係，包含分離型、分支型、交錯型、包圍型及重疊型。
本研究所發展的方法論中，首先將所得的資料轉換成圖形型態，利用影像處理技術濾除非系統性的缺陷點，再將鄰近的缺陷點加以匯整並計算密度，形成不同密度的方格，以獲取缺陷圖樣結構之訊息，在辨識核心部份，本研究分別採用了模板比對、元素分離、特徵萃取及特徵選取等手法，以期能發揮不同手法的優點，進而達成高準確度的辨識，另外在樣本描述及樣本分類的階段中，將樣本轉化為特徵向量，並將其投射至特徵空間，利用模糊理論之分群方法，將樣本分類並賦予其特定的信心程度。
本研究收集了某半導體廠商實際的缺陷資料，建立系統以驗證辨識方法的之可行性，以實證結果而言，本研究所提出之辨識方法相較於人工辨識，具有相當的準確性亦可大幅縮短辨識時間。

The semiconductor industry historically has been an extremely dynamic and high-growth business. Yield improvement is the important element to ensure the profitability. Defects incumber yield and increase the cost of manufacturing, so the defect inspection and recognition are vital in wafer fabrication. The development of recognition methodology is also the essential ingredient of yield enhancement.
This research intends to propose a high-efficiency solution of the pattern-related defects recognition based on the hybrid approach of pattern recognition. In this research we classify pattern-related defects into different categories including line, curve, ring, local, radial, repeat, and die edge. In addition to single-pattern problems we discussed before, this research also intends to solve the problems of multi-pattern recognition such that the practical applications can further be improved. There are five types of relationship in multi-pattern situation defined in this research, including separation, branch, crossover, encirclement and overlap. After transforming coordinate data into image format and using image processing techniques to eliminate the unsystematic noise and set grids to get structural information for further analysis. The procedures of hybrid identification technique performed in this methodology including templates matching, primitive separation, feature extraction and feature selection. By setting feature vectors into feature space and applying FCM theory to clustering, it is expected to reach the goal of description and classification.
The proposed methodology is verified with real industrial data and the experimental results show the advantages of high accuracy and short executing time.

ABSTRACT I
摘要 II
致謝辭 III
CONTENT IV
LIST OF FIGURE VI
LIST OF TABLE VIII
CHAPTER 1 INTRODUCTION 1
1.1 Research Background 1
1.2 Research Motivation 2
1.3 Research Objective 3
1.4 Research Methodology 4
1.5 Outline of Thesis 6
CHAPTER 2 LITERATURE REVIEW 7
2.1 An Overview of Semiconductor Manufacturing 7
2.1.1 The Manufacturing Process 9
2.1.2 The Discussion of Defects 14
2.2 Digital Image Processing 17
2.2.1 Introduction of Digital Image Processing 17
2.2.2 Noise Reduction 19
2.3 Pattern Recognition 22
2.3.1 Structural Pattern Recognition 26
2.3.2 Statistical Pattern Recognition 29
2.4 Clustering Theory 35
CHAPTER 3 METHODOLOGY 41
3.1 The Definition of Problem 41
3.2 The Methodology of Pattern-Related Defects Recognition 44
3.2.1 Defect Data Pre-processing 46
3.2.2 The Method of Hybrid Identification 48
3.2.3 The Method of Pattern Description 53
3.2.4 The Method of Pattern Classification 54
CHAPTER 4 IMPLEMENTATION AND VERIFICATION 56
4.1 Logistic of the Recognition System 56
4.2 System Implementation 58
4.2.1 The Frame of Recognition System 58
4.2.1 Main Functions of Recognition 60
4.3 System Verification 65
4.3.1 Verification of System Functions 66
4.3.2 Performance of Accuracy 69
4.3.3 Performance of Executing Time 72
CHAPTER 5 CONCLUSIONS 74
5.1 Summary 74
5.2 Further Research 77
REFERENCE 78
APPENDIX I 85
APPENDIX II 91

Andrzej, J. S. and Stephen, W., “A Pattern Recognition Based Method for IC failure Analysis,” IEEE Transactions Computer-Aided Design, 76-92(1985.)
Anil, K. Jain, Robert, P.W. Duin, and Jianchang, Mao, “Statistical Pattern Recognition: A Review,” IEEE transaction on pattern analysis and machine intelligence, 22(1), 4-37(2000).
Ankerst, M., Breuning, M., Kriegel, H. P. and Sander, J., “OPTICS: Ordering points to identity the clustering structure,” Proceedings of the 1999 ACM SIGMOD international conference on Management of data, 28(2), 49-60(1999).
Baxes, Gregory A., “Digital image processing: principles and applications,” John Wiley and Sons, 1994.
Bow, Sing-Tze, “Pattern Recognition and Image Processing,” Marcel Dekker, 2002.
Breaux, L. and Singh, B., “Automatic defect classification system for patterned semiconductor wafers,” IEEE/UCS/SEMI International Symposium on Semiconductor Manufacturing, 68–73(1995).
Chen, Y. F. and Nazir, A. W., “A Knowledge-Based System for Multiple Pattern Recognition Paradigms Support” IEEE Transactions Computer-Aided Design, 1130-1135(1995).
Carpenter, Gail A., Grossberg, Stephen, “A Massively Parallel Architecture for a Self-Organizing Neural Pattern Recognition Machine,” Computer Vision Graphics Image Processing, 54-115(1987).
Chen, F. L. and Liu, S. F., “A neural-network approach to recognize defect spatial pattern in semiconductor manufacturing,” IEEE Transactions on Semiconductor Manufacturing, 13(3), 366-373(2000).
Chuai-aree, S., Lursinsap, C., Sophatsathit, P. and Siripant, S., “Fuzzy C-Mean: A Statistical Feature Classification of Text and Image Segmentation Method,” International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 9(6), 661-671(2001).
Cunningham, S.P. and MacKinnon, S., “Statistical methods for visual defect metrology,” IEEE Transactions on Semiconductor Manufacturing, 11(1), 48-53(1998).
Ester, M., Kriegel, H. P., Sander, J. and Xu, X., “A density-based algorithm for discovering clusters in large spatial databases,” Conf. Knowledge Discovery and Data Mining, 226-331(1996).
Ferri, F., Pudil, P., Hatef, M. and Kittler, J., “A Comparative Study of Techniques for Large Scale Feature Selection,” Pattern Recognition in Practice IV, 403-413(1994).
Flury, B., “Common Principal Components and Related Multivariate Models” Wiley, NewYork, 1988.
Friedman, D. J. and Albin, S. L., “Clustered defects in IC fabrication: Impact on process control charts,” IEEE Transaction Semiconductor Manufacturing, 4(1),3642(1991).
Friedman, J. H., “Exploratory Projection Pursuit,” J. Am. Statistical Assoc., vol. 82, pp. 249-266(1987).
Fu, K. S., “Syntactic Pattern Recognition and Applications,” PrenticeHall, Englewood Cliffs, New Jersey, 1982.
Fukunaga, Keinosuke, “Introduction to Statistical Pattern Recognition,” Library of Congress Cataloging-in-Publication Data, 1990.
Fukushima, T., Narazaki, H. and Konishi, M., “A method of feature extraction from an image for quality analysis,” IEEE International Conference on Systems, Man, and Cybernetics, 2, 952-957(1999).
Goldfarb, Lev, “A Unified Approach to Pattern Recognition,” Pattern Recognition, 17(5):575–582(1984).
Gonzalez, R. C., Woods, R. E., Rafael, C. G. and Richard, E. W., “Digital image processing,” Prentice Hall, 2002.
Guha, Sudipto, Rastogi, Rajeev, and Shim, Kyuseok, “CURE: An Efficient Clustering Algorithm for Large Databases,” ACM-SIGMOD International Conference on Management of Data, 73-84(1998).
Hall, Ernest. L., “Computer image processing and recognition,” Academic Press, 1979.
Han, J. and Kamber, M., “Data Mining: Concepts and Techniques,” Morgan Kaufmann Publishers, 2001.
Haykin, S., Neural Networks, “A Comprehensive Foundation. Second ed,” Englewood Cliffs, N.J.: Prentice Hall, 1999.
Hsieh, H. W. and Chen, F. L., “Recognition of defect spatial patterns in semiconductor fabrication,” International Journal of Production Research, 42(19), 4153-4172(2004).
Huang, C. J., Wu, C. F. and Wang, C. C., “Image processing techniques for wafer defect cluster identification,” IEEE Design & Test of Computers, 19(2), 44- 48(2002).
Huang, Chenn-Jung, Wang, Chua-Chin, and Wu, Chi-Feng, “Image Processing Techniques for Wafer Defect Cluster Identification,” IEEE Design and Test of Computers, 44-74(2002).
Iwata, H., Ono, M., Konishi, J., Isogai, S. and Furutani, T., “In-line wafer inspection data warehouse for automated defect limited yield analysis,” Advanced Semiconductor Manufacturing Conference, 124-129(2000).
James, F., Leonid, B. V., Vladimir, V. Kirzon-Zolin, and Vadim, G. Schukin, “Application of pattern recognition and image classification techniques to determine continuous cardiac output from the arterial pressure waveform,” IEEE transactions on biomedical engineering 42(10), 913-920(1994).
John, C. Russ, “The Image Processing Handbook,” CRC press, 1992.
Kuroda, Kazuhiro, Harada, Ken, and Hagiwara, Masafumi, “Large Scale OnLine
Handwritten Chinese Character Recognition Using Improved Syntactic Pattern Recognition,” In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics , 4530-4535(1997).
Kohonen, T., “The self organizing maps,” Proc. IEEE, 78(9), 1464-1480(1990).
Koski, Antti, Juhola, Martti, and Meriste, Merik, “Syntactic Recognition of ECG Signals by Attributed Finite Automata,” Pattern Recognition, 28(12), 1927–1940(1995).
Krishna, K., Murty, M.N., “Genetic k-means algorithms,” IEEE Transactions System Management Cybernet.-B: Cybernet. 29(3), 433-439(1999).
Krishnapuran, R., Joshi, A., Nasraoui, O., Yi, L., “Low-complexity fuzzy relational clustering algorithms for web mining,” IEEE Transactions Fuzzy System, 9(4), 595-607(2001).
Liao, T. Warren, “Clustering ofime series data-a survey,” The journal of the pattern recognition society, 1857-1874(2005).
Maly, W. and Deszczka, J., “Yield estimation model for VLSI artwork evaluations,” Electron. Lett., 19(6), 226–227(1983).
Mar,c L., Maty, M. and Dan, Y., “DCS-1: a fuzzy logic expert system for automatic defect classification of semiconductor wafer defects,” IEEE World Congress on Computational Intelligence, 2100–2106(1994).
Marques, de Sa J. P., “Pattern Recoanition Concepts, Methods and Applications,” Springer, 2001.
Nemoto, K., Ikeda, S., Yoshida, O., Sasabe, J. and Su, H., “A statistical method for reducing systematic defects in the initial stages of production,” Advanced Semiconductor Manufacturing Conference, 77–81(2002).
Neyer, T. and Hafner, M., “Yield learning using the defect reticle method,” Advanced Semiconductor Manufacturing Conference, 110-114(2004).
Nurani, R. K., Akella, R., and Strojwas, A. J., “In-line defect sampling methodology in yield management: An integrated framework,” IEEE Transaction Semiconductor Manufacturing., 506–517(1996).
Olszewski, Robert T., “Generalized Feature Extraction for Structural Pattern Recognition in Time Series Data,” Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy, 2001.
Raman, K. N., Andrzej, J. S., Wojciech, P. M., and Charles, Ouyang, “In-Line Yield Prediction Methodologies Using Patterned Wafer Inspection Information,” IEEE Transaction on Semiconductor Manufacturing, 11(1), 40-47(1998).
Rengaswamy, Raghunathan and Venkatasubramanian, Venkat, “A Syntactic PatternRecognition Approach for Process Monitoring and Fault Diagnosis,” Engineering Applications of Artificial Intelligence, 8(1), 35–51(1995).
Rangachar, Kasturi, Mohan, M. T.., “Image analysis applications,” M. Dekker, 1990.
Segal, J., Sagatelian, A., Hodgkins, B., Chu. B., Singh, T. and Berman, H., “Critical area based yield prediction using in-line defect classification information [DRAMs],” Advanced Semiconductor Manufacturing Conference, 83-88(2000).
Sergios, Theodoridis and Konstantinos, Kuotroumbas, “PATTERN RECOGNITION,” An imprint of Elsevier, 2003.
Shin, C. K. and Park, S. C., “A machine learning approach to yield management in semiconductor manufacturing,” International Journal of Production Research, 17(38), 4261-4271(2000).
Trahanias, Panagiotis and Skordalakis, Emmanuel, “ Syntactic Pattern Recognition of the ECG,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(7), 648–657(1990).
Vaughan, R.A., “Pattern recognition and image processing in physics,” Proceedings of the thirty-seventh scottish universities summer school in physics, 1-15(1990).
Wan,g Wei, Yang, Jiong, and Muntz, Richard, “STING: A Statistical Information Grid Approach to Spatial Data Mining,” International conference on very large data base, 186-195(1997).
Webb, A.R., “Multidimensional Scaling by Iterative Majorization Using Radial Basis Functions,” Pattern Recognition, 28(5), 753-759(1995).
Webb, A. R., “Statistical Pattern Recognition,” John Willy and Sons, 2002.
Zhang, T., Ramakrishnan, R. and Livny, M., “Birch: An efficient data clustering method for very large database,” Proceedings of the ACM SIGMOD international conference on Management of data, 25(2), 103-114(1996).