電腦視覺已經廣泛的應用在電子元件的線上即時檢測中。本論文即針對各種元件的缺陷有效結合數種演算法，以發展準確快速的印刷電路板插件檢測系統為目標。印刷電路板插件檢測系統主要可以分為影像分割及影像處理兩大部份。在影像分割中，應用Sobel運算子針對影像亮度分量處理印刷電路板快速定位問題，另分別應用倒傳遞類神經法則及結合與分類中心相比較的FCM（Fuzzy c-Means）聚類演算法，有效分割彩色影像中物件與非物件圖素。之後針對所得的二值影像，應用跑長平滑概念與跑長標記的影像處理技術予以雜訊消除與元件定位，並以左右像素落點差擷取元件特徵資訊判斷元件倒置缺陷。最後透過模擬的結果取得各演算法最佳參數調校，並將上述所有理論技術整合建構成一實際的印刷電路板插件檢測系統。

Computer vision has been widely used in on-line inspection of electronic components. In this paper, we present a printed circuit board (PCB) inspection system based on computer vision using several methods, which provides us with an efficient solution for inspecting all kinds of mistakes of component. The PCB inspection system can be divided into two phases: (1) image segmentation and (2) image processing. In image segmentation, we locate the position of PCB by using sobel operator in intensity of image. Then we process our color image with bi-level quantization by using back-propagation neural network and fuzzy c-means clustering method in combination with the algorithm of compared with cluster centers. In part of image processing, we use run-length smoothing in noise cancellation and use run-length labeling to fix the position of component; furthermore we extract character of those components by left and right fallen-point feature extraction. Finally, we simulate the best parameters for all methods, and build the accurate, repeating, and flexible system to inspect components in PCB.

中文摘要..................................................I
英文摘要.................................................II
誌 謝................................................III
目 錄.................................................IV
圖表索引................................................VII
第一章緒論.............................................1
1.1 研究動機...................................1
1.2 發展方向與目的.............................3
1.3 主要貢獻...................................5
1.4 論文架構...................................6
第二章系統架構.........................................8
2.1 硬體設備...................................9
2.2 印刷電路板檢測流程........................11
第三章色彩模型........................................13
3.1 RGB色彩模型...............................14
3.2 CMY＆CMYK色彩模型.........................15
3.3 YIQ色彩模型...............................16
3.4 HSI色彩模型...............................17
3.4.1 由RGB轉換至HSI色彩模型...............19
3.4.2 由HSI轉換至RGB色彩模型...............23
3.5 HSV&HSB色彩模型...........................26
3.6 HLS色彩模型...............................29
第四章影像分割........................................33
4.1 梯度運算子................................34
4.2 倒傳遞類神經網路..........................38
4.2.1學習演算法.............................39
4.2.2回想演算法.............................44
4.2.3演算法的推導...........................44
4.3 結合與分類中心相比較的FCM聚類演算法.......48
4.3.1 FCM聚類演算法........................49
4.3.2 與分類中心相比較法...................51
第五章 影像處理........................................52
5.1 雜訊消除..................................52
5.2 影像標記..................................54
5.2.1 四連通標記法.........................55
5.2.2 跑長標記法...........................57
5.3 左右像素落點差特徵抽取法..................59
第六章系統模擬與實現..................................63
6.1影像分割.....................................64
6.1.1 Sobel運算子臨界值選取................64
6.1.2 倒傳遞類神經演算法特徵分析...........65
6.1.3 FCM聚類演算法特徵分析................76
6.2 影像處理..................................85
6.2.1 雜訊消除與元件定位...................85
6.2.2 特徵向量萃取.........................86
6.3 系統實現..................................88
6.3.1 離線訓練.............................88
6.3.2 線上檢測.............................95
第七章結論與未來展望.................................100
7.1 結論.....................................100
7.2 未來展望.................................101
參考文獻................................................103
作者簡介................................................106
授權書..................................................107

[1]Buscher, S. M., G. Burroughs, and etc., “2001 Industry Vision Forecast,” SMT, Vol. 14, No. 12, December 2000.
[2]Strauss, R., Surface Mount Technology, Butterworth-Heinemann, 1994.
[3]Raymond, D. W. and D. F. Haigh, “Why Automate Optical Inspection?,” IEEE International Test Conference, pp. 1033, 1997.
[4]Bob, R., “New Advances in AOI Technologies,” SMT, Vol. 15, No. 1, January 2001.
[5]廖晏生，“電腦視覺在電路板檢測上的應用”，國立交通大學機械工程研究所，1997。
[6]李德修，“彩色影像分類和檢測框法在電路板元件檢測上的應用”，國立交通大學機械工程研究所，1999。
[7]謝享奇，“模糊聚分析在數位影像辨識的應用”，國立臺灣科技大學電機工程所碩士論文，2000。
[8]Horng-Hai, Loh and Lu Ming-Sing, “Printed Circuit Board Inspection Using Image Analysis,” IEEE Transactions on Industry Applications, Vol. 35, No. 2, March/April 1999.
[9]David, E. and D. Cihan, “Automated Misplaced Component Inspection for Printed Circuit Boards,” Computers ind. Engng. ,Vol. 33, Nos 1-2, pp. 373-376, 1997.
[10]Johnson, R. B., “Recognising Electronic Symbols Using Neural Networks,” IEE Colloquium on Document Image Processing and Multimedia, pp. 4/1-4/4, March 1999.
[11]電子技術編輯群，“表面黏著技術（SMT）”，電子技術出版社，1989。
[12]Fortner, B. and T. E. Meyer, Number by Colors: A Guide to Using Color to Understand Technical Data, TELOS, 1997.
[13]Gonzalez, R. C. and R. E. Woods, Digital Image Processing, Addison-Wesley, 1993.
[14]徐法坤，“數位影像色彩管理”，龍溪國際圖書有限公司，1999。
[15]Foley, J. D., A. V. Dam, S. K. Feiner, and J. F. Hughes, Computer Graphics: Principles and Practice, Addison-Wesley, 1996.
[16]王進德，蕭大全，“類神經網路與模糊控制理論入門”，全華科技圖書股份有限公司，1999。
[17]Haykin, S., Neural Networks, Prentice Hall Inc., 1999.
[18]Principe, J. C., N. R. Euliano and W. C. Lefebvre, Neural and Adaptive Systems, John Wiley & Sons Inc., 2000.
[19]Klir, G. J. and B. Yuan, Fuzzy Sets and Fuzzy Logic, Prentice Hall Inc., 1995.
[20]Mahmoud, R. R., P. M. J. van der Zwet, B. P. F. Lelieveldt, R. J. van der Geest, J. H. C. Reiber and Senior Member,“A Multiresolution Image Segmentation Technique Based on Pyramidal Segmentation and Fuzzy Clustering”, IEEE Transactions on Image Processing, Vol. 9, No. 7, pp. 1238-1248, July 2000.
[21]Reazee, M. R., C. Nyqvist, P. M. J. van der Zwet, E. Jansen, and J. H. C. Reiber, “Segmentation of MR Images by a Fuzzy C-means Algorithm,” Proceedings of Computers in Cardiology , pp.21-24, 1995.
[22]Wong, K. Y., R. G. Casey, and F. M. Wahl, “Document Analysis System,” IBM Journal of Research and Development, Vol. 26, No. 6, pp.647-656, November 1982.
[23]Fisher, J. L., S. C. Hlnds, and Donald P. D’Amato, “A Rule-based System for Document Image Segmentation,” Proceedings of the 10th IEEE International Coference on Pattern Recognition, Vol. 1, pp.567-572, 1990.
[24]Shih, F. Y. and Shy-Shyan Chen, “Adaptive Document Block Segmentation and Classification,” IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics, Vol. 26, No. 5, October 1996.
[25]Haralick, R. M. and L. G. Shapiro, Computer and Robot Vision, Addison-Wesley, Vol. 1, 1992.
[26]Zenzo, S. D., L. Cinque, and S. Levialdi, “Run-Based Algorithms for Binary Image Analysis and Processing,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, No. 1, January 1996.
[27]Haralick, R. M. and L. G. Shapiro, Computer and Robot Vision, Addison-Wesley, Vol. 2, 1992.