臺灣博碩士論文加值系統

在半導體產業中為了獲得好的良率，在晶粒封裝前的晶圓缺陷檢測是一個很重要的過程。傳統的晶圓缺陷檢測方法通常是由數十位檢測人員透過電子顯微鏡由肉眼去做檢測，並且把晶圓上有缺陷的區域標記出來。這種以人力的判斷方式也可能會因為人力疲勞或經驗不足產生誤判。除此之外，傳統的方式也會產生一些額外的人力花費。為了解決上述的缺點，本論文將發展一個可以自動地辨識缺陷樣本的檢測系統。我們採用半徑基底函數(RBF)類神經網路來進行晶粒外觀的檢測。實驗的結果顯現提出的半徑基底函數(RBF)類神經網路可以成功地辨識出在LED晶元影像上有缺陷的晶粒，而且有好的效能。

Wafer defect inspection is an important process before die packaging, because a good yield ratio is key index to earn benefit in semiconductor manufacturing. Conventional wafer inspection was usually performed by human visual judgment. A large number of people visually examine wafers and hand-mark the defective regions. As a result, potential misjudgment may be introduced due to human fatigue. Besides, traditional method bring out a considerable personnel cost. In order to solve these shortcomings, our research intends to develop an automatic inspection system, which recognizes defective patterns automatically. The Radial Basis Function (RBF) neural network was adopted for inspection processing. Actual data obtained from a semiconductor manufacturing company in Taiwan were used in experiments. The experimental results show the proposed RBF neural network successfully identifies the defective dies on LED wafers images with good performance.

中文摘要 ------------------------------------------------------------------i
英文摘要 ------------------------------------------------------------------ii
致謝 ------------------------------------------------------------------iii
目錄 ------------------------------------------------------------------iv
圖目錄 ------------------------------------------------------------------vi
表目錄 ------------------------------------------------------------------viii
第一章 簡介--------------------------------------------------------------1
1.1 問題描述----------------------------------------------------------1
1.2 研究動機----------------------------------------------------------1
1.3 研究目的----------------------------------------------------------2
1.4 論文大綱----------------------------------------------------------4
第二章 文獻回顧----------------------------------------------------------5
2.1 簡介--------------------------------------------------------------5
2.2 知識型的資料庫方法------------------------------------------------5
2.3 晶圓缺陷群集識別--------------------------------------------------6
2.4 監督式類神經網路為主的方法----------------------------------------7
2.5 非監督式類神經網路為主的方法--------------------------------------10
2.6 文獻回顧與本論文的關聯--------------------------------------------12
第三章 LED晶元缺陷檢測方法-----------------------------------------------13
3.1 前處理------------------------------------------------------------15
3.1.1 中間值濾波器------------------------------------------------------15
3.1.2 亮度校正----------------------------------------------------------16
3.1.3 晶粒位置與大小----------------------------------------------------16
3.1.4 擷取電極區與發光區------------------------------------------------21
3.2 特徵擷取----------------------------------------------------------23
3.3 Otsu’s Method----------------------------------------------------25
3.4 半徑基底函數(RBF)類神經網路---------------------------------------28
3.5 檢測過程----------------------------------------------------------31
第四章 實驗結果----------------------------------------------------------33
4.1 實驗資料來源------------------------------------------------------33
4.2 特徵選取的探討----------------------------------------------------35
4.3 半徑基底函數類神經網路參數探討------------------------------------39
4.4 中心點選擇的探討--------------------------------------------------41
4.5 實驗結果----------------------------------------------------------42
4.6 實驗比較----------------------------------------------------------46
4.7 效能評估----------------------------------------------------------48
第五章 結論--------------------------------------------------------------52
參考文獻 ------------------------------------------------------------------53
附錄 Radial-Basis Function Neural Networks for LED Wafer Defect Inspection----------------------------------------------------55

[1]Chao-To Su, Taho Yang, Chir-Mour Ke, “Neural-Network Approach for Semiconductor Wafer Post-Sawing Inspection,” IEEE Transactions on Semiconductor Manufacturing , Vol. 15, No. 2, pp.260-266, 2002.
[2]Kenneth W. Tobin, Jr., Thomas P. Karnowski, Fred Lakhani, “Integrated Applications of Inspection Data in the Semiconductor Manufacturing Environment,” SPIE, Metrology-based Control for Micro-Manufacturing, Vol. 4275, pp. 31-40, 2001.
[3]Mital, D.P. Teoh, E.K. “Computer Based Wafer Inspection System,” Proceeding of International Conference on Industrial Electronics, Control and Instrumentation, Vol. 3, pp. 2497-2503, 1991.
[4]J.-M. Zhang, R.-M. Lin, and M.-J. Wang, “The Development of an Automatic Post-Sawing Inspection System Using Computer Vision Techniques,” Computers in Industry, Vol. 30, pp. 51-60, 1999.
[5]Chuan-Yu Chang, H.-J. Wang and S.-Y. Lin, “Simulation Studies of Two-layer Hopfield Neural Networks for Automatic Wafer Defect Inspection”, Lecture Notes in Computer Science, vol. 4031. pp. 1119-1126, 2006.
[6]Chuan-Yu Chang and Pau-Choo Chung, “Two Layer Competitive Based Hopfield Neural Network for Medical Image Edge Detection,” Optical Engineering, Vol. 39, no. 3, pp. 695-703, 2000.
[7]Chuan-Yu Chang, "Contextual Hopfield Neural Networks for Medical Image Edge Detection”, Optical Engineering, Vol. 45, Issue 3, pp. 037006-037014, March 2006.
[8]Rafael C. Gonzalez, Richard E. Woods, “Digital Image Processing 2nd”, Prentice-Hall International, Inc. 2002.
[9]N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Transactions on Systems Man Cybernet, vol. 9, pp. 62-66, 1979.
[10]Manuel G. Penedo, Maria J. Carreria, Antonio Mosquera, and Diego Cabello, “Computer-Aided Diagnosis: A Neural-Network-Based Approach to Lung Nodule Dtection”, IEEE Trans. On Medical Imaging, vol. 17, pp. 872-880, 1998.
[11]Chuan-Yu Chang, Jia-Wei Chang, and MuDer Jeng, “Using a self-organizing neural network for defect inspection”, Systems, Man and Cybernetics, IEEE International Conference, vol. 5, pp. 4312-4317, 2004.
[12]Fei-Long Chen; Shu-Fan Liu; “A neural-network approach to recognize defect spatial pattern in semiconductor fabrication,” IEEE Transactions on Semiconductor Manufacturing, Vol. 13, No. 3, PP. 366 – 373, 2000.
[13]Chenn-Jung Huang, Chi-Feng Wu, Chua-Chin Wan, “Image processing techniques for wafer defect cluster identification” IEEE Design & Test of Computers, vol. 19, no. 2, pp.44-48, 2002.
[14]Rein-Lien Hsu, Mohamed Abdel-Mottaleb, Anil K. Jain, “Face Detection in Color Image”, IEEE Transactions on Patten Analysis and Machine Intelligence, Vol. 24, No. 5, May 2002.
[15]張嘉偉，2005，使用自組式類神經網路在晶圓缺陷檢測系統，國立雲林科技大學，碩士論文。
[16]林思延，2006，霍普菲爾類神經網路應用於自動化半導體晶圓污損檢測，國立雲林科技大學，碩士論文。