臺灣博碩士論文加值系統

各產業中都可以看見自動化光學檢測(Automated Optical Inspection，統稱AOI)
的技術，而在現今的工廠自動化產線，AOI 設備更是不可或缺的環節之一。目前，
絕大部分的產線在沒有AOI 設備的情況下是不會開線的。
而AOI 在傳統處理方法上，都是先對樣品打光取像，接著做影像前處理，把
感興趣的地方突顯出來，再進行影像特徵擷取，把影像像素轉換為特徵資料，最後
再透過分類或辨識的演算法使用這些特徵資料來做判斷與檢測。此種方法需要工
程師們花費大量的時間去定義特徵以及演算法開發，而且傳統的方法對樣品特徵
很敏感，只要換了另一批樣品，就必須重新定義特徵以及演算法的參數。
因此，本研究使用人工智慧深度學習的方法，進行自動化光學檢測之研究，以
銅箔影像為研究對象，引入卷積神經網路(CNN)演算法，提出一個瑕疵分類
(Classification)的方法。

The technology of Automated Optical Inspection (AOI) can be seen in all industries. Nowadays, AOI equipment is one of the indispensable technology in factory automated production line. Most of the production lines cannot work without an AOI equipment until now.
The AOI process in the traditional processing is as follows. First, the sample of image is captured by flash light, and then do the pre-processing to highlight the area of interest. The image is subjected to feature extraction to convert image pixels into feature data. Finally, these feature data are used for judgment and inspection through classification or identification algorithms. This approach requires engineers to spend a lot of time defining features and algorithm development, and traditional methods are sensitive to sample characteristics. As long as you change another batch of samples, you
must redefine the features and parameters of the algorithm.
Therefore, this study utilizes the method of artificial intelligence deep learning to conduct automated optical inspection research. A method of classification is proposed, which takes copper foil image as the research object and adds the convolutional neural network (CNN) algorithm.

摘要 i
ABSTRACT ii
誌謝 iii
目錄 iv
表目錄 vii
圖目錄 viii
第1章 緒論 1
1.1 研究背景 1
1.2 文獻探討 1
1.3 研究動機與目的 3
1.4 論文架構 4
第2章 基本理論介紹 5
2.1 相機介紹 5
2.2 鏡頭介紹 6
2.3 光源介紹 8
2.4 類神經網路(Neural Network) 8
2.5 卷積神經網路(Convolutional Neural Network) 16
第3章 研究方法 20
3.1 銅箔軟體系統設計 20
3.2 銅箔瑕疵介紹 21
3.3 銅箔瑕疵檢測 23
3.4 銅箔瑕疵分類 25
第4章 實驗結果 30
4.1 系統開發環境 30
4.2 實驗結果-線相機模組 CF Linescan 31
4.3 實驗結果-參數管理模組 CF Parameters Manager 40
4.4 實驗結果-系統監測模組 CF System Monitor 41
4.5 實驗結果-通訊模組 CF LINK 43
4.6 實驗結果-影像分析模組 CF Image Analysis 43
4.7 實驗結果-銅箔影像即時影像前處理與瑕疵檢測 46
第5章 結論與未來展望 48
5.1 結論 48
5.2 未來展望 48
參考文獻 49

期刊論文
1.Y. Santur, M. Karaköse, and E. Akin, "A new rail inspection method based on deep learning using laser cameras," in 2017 International Artificial Intelligence and Data Processing Symposium (IDAP), 2017, pp. 1-6.
2.X. Zhang, K. Wang, Y. Wang, Y. Shen, and H. Hu, "An improved method of rail health monitoring based on CNN and multiple acoustic emission events," in 2017 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 2017, pp. 1-6.
3.L. Shang, Q. Yang, J. Wang, S. Li, and W. Lei, "Detection of rail surface defects based on CNN image recognition and classification," in 2018 20th International Conference on Advanced Communication Technology (ICACT), 2018, pp. 45-51.
4.J. Kim, S. Kim, N. Kwon, H. Kang, Y. Kim, and C. Lee, "Deep learning based automatic defect classification in through-silicon Via process: FA: Factory automation," in 2018 29th Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC), 2018, pp. 35-39.
5.G. Tello, O. Y. Al-Jarrah, P. D. Yoo, Y. Al-Hammadi, S. Muhaidat, and U. Lee, "Deep-Structured Machine Learning Model for the Recognition of Mixed-Defect Patterns in Semiconductor Fabrication Processes," IEEE Transactions on Semiconductor Manufacturing, vol. 31, no. 2, pp. 15-322, 2018.
6.Y. Sun and H. Long, "Detection of Weft Knitting Fabric Defects Based on Windowed Texture Information And Threshold Segmentation by CNN," in 2009 International Conference on Digital Image Processing, 2009, pp. 292-296.
7.黃振珂, "基於卷積神經網路之輪胎氣泡缺陷檢測," 碩士, 資訊工程系, 國立雲林科技大學, 雲林縣, 2017.
8.J. Zhong, Z. Liu, Z. Han, Y. Han, and W. Zhang, "A CNN-Based Defect Inspection Method for Catenary Split Pins in High-Speed Railway," IEEE Transactions on Instrumentation and Measurement, pp. 1-12, 2018.
9.A. Khumaidi, E. M. Yuniarno, and M. H. Purnomo, "Welding defect classification based on convolution neural network (CNN) and Gaussian kernel," in 2017 International Seminar on Intelligent Technology and Its Applications (ISITIA), 2017, pp. 261-265. 50
10.L. M. Azizah, S. F. Umayah, S. Riyadi, C. Damarjati, and N. A. Utama, "Deep learning implementation using convolutional neural network in mangosteen surface defect detection," in 2017 7th IEEE International Conference on Control System, Computing and Engineering (ICCSCE), 2017, pp. 242-246.
11.曹瑋宸, "基於深度學習之性別辨識與人員計數," 碩士, 資訊工程系, 國立雲林科技大學, 雲林縣, 2016.
12.Y. Shi, Y. Li, X. Wei, and Y. Zhou, "A Faster-RCNN Based Chemical Fiber Paper Tube Defect Detection Method," in 2017 5th International Conference on Enterprise Systems (ES), 2017, pp. 173-177.
13.K. Han, M. Sun, X. Zhou, G. Zhang, H. Dang, and Z. Liu, "A new method in wheel hub surface defect detection: Object detection algorithm based on deep learning," in 2017 International Conference on Advanced Mechatronic Systems (ICAMechS), 2017, pp. 335-338.
14.S. J. Lee, J. Ban, H. Choi, and S. W. Kim, "Localization of slab identification numbers using deep learning," in 2016 16th International Conference on Control, Automation and Systems (ICCAS), 2016, pp. 1174-1176.
15.M. Yang, A. Nayeem, and L. Shen, "Plant classification based on stacked autoencoder," in 2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), 2017, pp. 1082-1086.
16.J. Yang, Y. Lee, and I. Koo, "Convolutional Autoencoder-Based Sensor Fault Classification," in 2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN), 2018, pp. 865-867.
17.S. Mei, H. Yang, and Z. Yin, "An Unsupervised-Learning-Based Approach for Automated Defect Inspection on Textured Surfaces," IEEE Transactions on Instrumentation and Measurement, vol. 67, no. 6, pp. 1266-1277, 2018.
18.F. Gao, Z. Li, G. Xiao, X. Yuan, and Z. Han, "An online inspection system of surface defects for copper strip based on computer vision," in 2012 5th International Congress on Image and Signal Processing, 2012, pp. 1200-1204.
19.R. Liang, Y. Ding, X. Zhang, and J. Chen, "Copper Strip Surface Defects Inspection Based on SVM-RBF," in 2008 Fourth International Conference on Natural Computation, 2008, vol. 2, pp. 41-45.
20.P. Wang, X. Zhang, Y. Mu, and Z. Wang, "The Copper Surface Defects Inspection System Based on Computer Vision," in 2008 Fourth International Conference on Natural Computation, 2008, vol. 3, pp. 535-539.
21.Z. Xuewu, L. Ruiyu, D. Yanqiong, C. Jiasheng, D. Dunqin, and Z. Guohua, "The system of copper strips surface defects inspection based on intelligent fusion," in 2008 IEEE International Conference on Automation and Logistics, 2008, pp. 476-51 480.
22.L. Wang and Y. Shen, "Design of Machine Vision Applications in Detection of Defects in High-Speed Bar Copper," in 2010 International Conference on EProduct E-Service and E-Entertainment, 2010, pp. 1-4.
23.T.-S. Li, "Applying wavelets transform and support vector machine for copper clad laminate defects classification," Computers & Industrial Engineering, vol. 56, no. 3, pp. 1154-1168, 2009/04/01/ 2009.
24.G. A. Al-Kindi, R. M. Baul, and K. F. Gill, "An application of machine vision in the automated inspection of engineering surfaces," International Journal of Production Research, vol. 30, no. 2, pp. 241-253, 1992/02/01 1992.
25.郭振鵬, "以系統單晶片架構做印刷電路板銅箔缺陷檢測系統之設計," 碩士, 電機工程學系碩博士班, 國立成功大學, 台南市, 2004.