晶圓在製造過程中難免會有一些缺陷，造成晶圓上的缺陷原因有很多種，因此，工程師透過晶圓針測結果產生的晶圓圖，觀察其錯誤晶粒分佈，進而分析製造過程中錯誤原因。以往總是由工程師以肉眼觀察晶圓圖找出特定的錯誤樣式，雖然人工偵測的方式可保證其正確率，但是卻非常缺乏效率。
本論文的目的即是透過機器學習的技術，讓電腦進行自動錯誤樣式分類，希望能藉此降低人力成本及晶圓分析的錯誤率。傳統方法是以原始晶圓圖上的位置進行資料分類，然而隨著晶圓資料集越來越大，此法可能會降低分類過程的效率。本論文所提出之方法著重於特徵擷取（feature extraction）的創新，我們根據晶圓圖的特性，找出幾何、Radon和其他等三大類的特徵值，大部分的特徵值皆具有旋轉不變（rotation-invariant）、尺度不變（scale-invariant）的特性，透過特徵擷取的方式，以一組特徵向量代表一張晶圓圖，分類器使用支撐向量機（support vector machine）。本論文共定義四種錯誤樣式，並將分類過程分為二個階段，第一階段辨別晶圓圖是否為錯誤樣式（pattern 或none），第二階段則辨別錯誤樣式的晶圓圖為四種特定錯誤樣式中的哪一類。
在實驗分析上，我們比較不同特徵對於系統分類辨識率變化，接著透過降維實驗自306維的特徵資料投影90維，其系統辨識率可高達91.1%。由實驗結果顯示，本論文提出的特徵值組合，對於大型資料集擁有良好的效率及辨識率結果，同時也證實我們提出的方法比起前人更能有效的區分不同晶圓圖的錯誤樣式。

　　In the process of wafer production, several causes might result in defect regions on a wafer. Defect causes can be identified by analyzing defect patterns on wafer maps obtained from chip probing. In the past, engineers need to manually inspect defect patterns on each wafer map. Although manual inspection guarantees an adequate accuracy for wafer failure pattern recognition, it is an inefficient and tedious task.
　　The purpose of this research is to perform automatic defect pattern classification through the use of machine learning techniques so that both the cost of human labor and the error rate in manual wafer analysis are reduced. Past method are to classify the data by using the raw wafer map location. However, this method is inefficient when the collected wafer data are large. The proposed method focuses on the innovation in feature extraction. Based on the characteristic of wafer maps, three types of feature are extracted: geometric, Radon and miscellaneous features. Most of feature types preserve the attribute of rotation-invariant and scale-invariant. Each wafer map is then represented by a feature vector. A support vector machine is used as the classifier. In this research, we define four failure patterns and divide the classification process in two stages. In the first stage, the system determines if the wafer map is either one of the four failure patterns or none of them. If the wafer map is determined as one of four failure patterns, the second stage of the system identifies which one of failure patterns the wafer is.
　　In the experiment, we examine the effectiveness of different features and the feature dimension is projected from 306 to 90 via dimensionality reduction. This yields a failure pattern recognition rate of 91.1%, which proves that the proposed method significantly outperform the previous method. The experimental result shows that the proposed features has satisfactory efficiency and accuracy result in large scale dataset.

摘要 I
Abstract II
謝誌 IV
目錄 V
圖目錄 VIII
表目錄 X
第一章 緒論 1
1.1 研究動機 1
1.2 研究背景 2
1.3 研究簡介 2
1.3.1 晶圓圖介紹 2
1.3.2 四大晶圓錯誤樣式說明 3
1.4 章節概要 4
第二章 相關研究 5
2.1 Wafer based clustering 5
2.2 Model based clustering 6
2.3 Feature based approach 7
第三章 研究方法 8
3.1 系統架構 8
3.2 特徵擷取 9
3.2.1 以晶圓的幾何資料為特徵 9
3.2.2 以Radon based為特徵 15
3.2.3 其他特徵 19
3.3 分類器介紹 22
3.3.1 支撐向量機 22
第四章 實驗結果 24
4.1 晶圓圖資料集簡介 24
4.2 實驗設定說明 25
4.2.1 環境設定 25
4.2.2 實驗流程與設計 25
4.2.3 效能評估方式 26
4.3 實驗一：以晶圓圖2×2的二元樣式的數量為特徵值 27
4.3.1 實驗目的與流程設定 27
4.3.2 實驗結果與分析 28
4.4 實驗二：以晶圓上的轉角點數量為特徵值 29
4.4.1 實驗目的與流程設定 29
4.4.2 實驗結果與分析 31
4.5 實驗三：透過特徵選取提升辨識結果 32
4.5.1 實驗目的與流程設定 32
4.5.2 實驗結果與分析 32
4.6 實驗四：降維實驗 35
4.6.1 實驗目的與流程設定 35
4.6.2 實驗結果與分析 37
4.7 實驗五：與現有方法比較 39
4.7.1 實驗目的與流程設定 39
4.7.2 實驗結果與分析 39
4.8 錯誤分析 41
第五章 結論與未來研究方向 46
5.1 結論 46
5.2 未來研究方向 48
參考文獻 49
附錄 52
附錄一　特徵擷取公式介紹 52
附錄二　比較使用不同的分類器辨識結果 55

[1] tsmc – 每季營運報告 [Online].
Available: http://www.tsmc.com/chinese/investorRelations/quarterly_results.htm
[2] L. Chen and S. F. Liu, “A neural-network approach to recognize defect spatial pattern in semiconductor fabrication,” IEEE Trans. Semicond. Manuf., vol. 13, no. 3, pp. 366–373, Aug. 2000.
[3] F. Chen, S. C. Hsu and Y. J. Chen, “A system for online detection and classification of wafer bin map defect patterns for manufacturing intelligence,” International Journal of Production Research, vol. 51, no. 8, pp. 2324-2338, Feb. 2013.
[4] J. Y. Hwang and W. Kuo, “Model-based clustering for integrated circuits yield enhancement,” Eur. J. Oper. Res., vol. 178, no. 1, pp. 143–153, 2007.
[5] T. Yuan and W. Kuo, “A model-based clustering approach to the recognition of spatial defect patterns produced during semiconductor fabrication,” IIE Trans., vol. 40, no. 2, pp. 93–101, 2008.
[6] T. Yuan and W. Kuo, “Spatial defect pattern recognition in semiconductor manufacturing using model-based clustering and Bayesian inference,” Eur. J. Oper. Res., vol. 190, no. 1, pp. 228–240, 2008.
[7] T. Yuan, S. J. Bae and J. I. Park, “Bayesian spatial defect pattern recognition in semiconductor fabrication using support vector clustering,” The International Journal of Advanced Manufacturing Technology, vol. 51, no. 5-8, pp. 671–683, Nov. 2010.
[8] T. Yuan, W. Kuo and S. J. Bae, “Detection of spatial defect patterns generated in semiconductor fabrication process,” IEEE Trans. Semicond. Manuf., vol. 24, no. 3, pp. 392–403, Aug. 2011.
[9] K. W. Tobin, S. S. Gleason, T. P. Karnowski, S. L. Cohen and F. Lakhani, “Automatic classification of spatial signatures on semiconductor wafer maps,” in Proc. Metrology, Inspection, and Process Control for Microlithography, 1997, pp.434–444.
[10] K. W. Tobin, S. S. Gleason, T. P. Karnowski, “Feature analysis and classification of manufacturing signatures based on semiconductor wafermaps,” in Proc. Machine Vision Applications in Industrial Inspection, 1997, pp. 14–25.
[11] T. P. Karnowski, K. W. Tobin, S. S. Gleason and Fred Lakhani, “The application of spatial signature analysis to electrical test data: validation study” in Proc. Inspection, and Process Control for Microlithography XIII, 1999, pp. 530–540.
[12] Shankar, N.G., Zhong, Z.W, “Defect detection on semiconductor wafer surfaces,” Microelectronics Engineering 77, 337–346, 2005a.
[13] Shankar, N.G., Zhong, Z.W, ”A new rule-based clustering technique for defect analysis,” Microelectronics Journal 36, 718–724, 2005b
[14] Radon, Johann （1917）, "Über die Bestimmung von Funktionen durch ihre Integralwerte längs gewisser Mannigfaltigkeiten", Berichte über die Verhandlungen der Königlich-Sächsischen Akademie der Wissenschaften zu Leipzig, Mathematisch-Physische Klasse [Reports on the proceedings of the Royal Saxonian Academy of Sciences at Leipzig, mathematical and physical section] （Leipzig: Teubner） （69）: 262–277
[15] C. Harris and M. Stephens, “A combined corner and edge detector”. Proceedings of the 4th Alvey Vision Conference. pp. 147–151, 1988.
[16] 朱俊霖，利用影像處理技術在晶圓缺陷及硬幣影像對位之應用，國立雲林科技大學碩士論文，民國96年。
[17] Chih-Chung Chang and Chih-Jen Lin, LIBSVM : a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1--27:27, 2011. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
[18] Whitney, "A direct method of nonparametric measurement selection", IEEE Transactions on Computers, vol. 20, pp.1100-1103, 1971.
[19] Y. Bengio, A. Courville and P. Vincent, “Representation learning: A review and new perspectives,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 35, no. 8, pp. 1798–1828, Aug. 2013.
[20] G. E. Hinton and R. R. Salakhutdinov, “Reducing the dimensionality of data with neural networks,” Science, vol. 313, no. 5786, pp. 504–507, Jul. 2006.
[21] G. E. Hinton, “Training a deep autoencoder or a classifier on MNIST digits,” [Online]. Available: http://www.cs.toronto.edu/~hinton/MatlabForSciencePaper.html