臺灣博碩士論文加值系統

目前印刷電路板（Printed Circuit Board）表面的瑕疵檢驗系統，主要是針對線路幾何瑕疵檢測與表面黏著錫點檢測這二個方向，甚少對PCB電鍍表面進行瑕疵檢測的工作，且多僅利用灰階影像資訊進行影像分析，由於灰階影像所能提供的影像資訊（gray-value）不如彩色影像資訊（R, G, B）豐富，無法像彩色影像資訊能更完整的將影像資訊特徵呈現出來，因此本研究將利用彩色機器視覺技術，針對PCB之金手指（edge connector）電鍍表面進行自動瑕疵檢測。
本研究主要目標是發展一套適合於線上即時檢測的PCB金手指表面瑕疵檢測技術。由於目前的紋路瑕疵檢測技術多採用圖樣比對 (pattern match)或紋路特徵萃取（feature extraction）這兩大方向進行檢測的工作，因圖樣比對法缺點為比對效果會受旋轉、位移與光源的影響，而特徵萃取法於轉換的計算複雜導致計算時間長，不適合於即時性的生產檢測工作，因此本研究利用彩色影像資訊，藉由色彩模型轉換後的色彩特徵值選取，與資訊理論（information theory）中用於評估資訊內涵複雜度之量化衡量指標“熵”（entropy）結合，利用熵演算法的快速計算，衡量PCB電鍍表面（金手指）紋路的規則性與一致性，將破壞紋路規則性與一致性的瑕疵凸顯出來。
本研究分別提出利用雙色彩特徵資訊、紋路之方向角度資訊與熵結合，探討上述二種熵之檢測衡量指標對於金手指表面之色彩和結構瑕疵的檢測能力，由實驗結果得知，本研究對於金手指表面瑕疵具有良好的檢測凸顯能力，在其他工業產品的應用如紡織品、紙製品與金屬切削工件表面，本研究也能將破壞紋路規則性與一致性的瑕疵檢測凸顯出來。

Various automated visual inspection systems for printed circuit boards (PCBs) have been developed in the past years. However, most of the visual inspection techniques use only gray-level information of PCB images and focus mainly on line-etched defects. In this study, we employ color machine vision to inspect defects on electroplated surfaces of PCBs and in particular, edge connectors.
The electroplated surfaces of edge connectors can be considered as a homogeneous texture. Traditional texture analysis techniques such as co-occurrence matrix methods in the spatial domain, and Fourier-based features in the spectral domain are too computationally expensive to develop an efficient inspection system. In this study, we develop two entropy measures to evaluate the homogeneity of edge connector surfaces. One entropy measure uses two color features to detect color anomalies such as oxygenation, and the other uses edge angles to detect structural defects such as scratches on electroplated surfaces. Experimental results have shown that the purposed method is reliable in detection and efficient in computation. It takes only 1 second to detect 7 edge-connector pins in one image.

中文摘要………………………………………………………………… I
英文摘要………………………………………………………………… II
目錄……………………………………………………………………… III
表目錄…………………………………………………………………… V
圖目錄…………………………………………………………………… VI
第一章 緒論……………………………………………………………… 1
1.1 研究動機與目的…………………………………………………… 1
1.2 金手指瑕疵分類簡介……………………………………………… 2
1.3 研究範疇及限制…………………………………………………… 4
1.4 研究方法簡介……………………………………………………… 4
第二章 文獻回顧………………………………………………………… 6
2.1 PCB自動檢測… …………………………………………………… 6
2.2 規則性與熵之衡量………………………………………………… 9
2.3 紋路分析…………………………………………………………… 11
第三章 研究方法 ……………………………………………………… 14
3.1 熵演算法…………………………………………………………… 14
3.2 色彩模型…………………………………………………………… 15
3.3 熵的色彩規則性檢測……………………………………………… 18
3.3.1 單一色彩特徵值指標檢測…………………………………… 19
3.3.2 雙色彩特徵組合指標檢測…………………………………… 22
3.4 熵的方向規則性檢測……………………………………………… 26
3.5 彩色影像瑕疵檢測………………………………………………… 31
第四章 初步實驗分析與討論 ………………………………………… 35
4.1 系統架構與實驗環境……………………………………………… 35
4.2 敏感度分析………………………………………………………… 37
4.2.1 色彩特徵值之有效值範圍改變的影響……………………… 38
4.2.2 逐點檢測與抽樣點檢測的影響……………………………… 42
4.2.3 檢測視窗大小的影響………………………………………… 46
4.2.4 特徵值區間數變動之影響…………………………………… 48
4.2.5 管制界限的設定……………………………………………… 52
4.3 色彩特徵組合之檢測影響………………………………………… 55
4.3.1 色彩變異瑕疵之檢測………………………………………… 56
4.3.2 結構性變異瑕疵之檢測……………………………………… 74
4.3.3 大範圍粗糙瑕疵之檢測……………………………………… 80
4.3.4 檢測流程設定………………………………………………… 82
4.3.5 檢測實驗統計分析…………………………………………… 85
4.4 非金手指檢測應用………………………………………………… 90
4.4.1 紡織品與金屬加工件之瑕疵檢測…………………………… 90
4.4.2 紙製品之瑕疵檢測…………………………………………… 97
4.5 實驗結果之結論……………………………………………………104
第五章 結論與建議…………………………………………………… 106
參考文獻………………………………………………………………… 108
附錄一…………………………………………………………………… 112
附錄二…………………………………………………………………… 113

Ahmed, H. D. and Steven, A. H., 1990, “Entropy Measures for Texture Analysis Based on Hadamard Transform”, Proceedings of IEEE Southeastcon, Vol. 2, pp. 467-470.
Capson, D. W. and Eng, S. K., 1988, “A Tiered-Color Illumination Approach for Machine Inspection of Solder Joints”, IEEE Transactions on Pattern analysis and Machine Intelligence, Vol. 10, pp. 387-393.
Chang, C. A., Lin, H. D. and Lo, C. C., 1997, “Test of Pattern Change for Automated Detection of Printing Faults Using Computer Vision Systems”, International Journal of Industrial Engineering, Vol. 4, pp. 5-13.
Chi, Z. and Geman, S., 1998, “On the Consistency of Minimum Complexity Nonparametric Estimation”, IEEE Transactions on Information Theory, Vol. 44, pp. 1968-1973.
Dawson, B. R. P. and Parsons, A. J., 1994, “Texture Measure for the Identification and Monitoring of Urban Derelict Land”, International journal of Remote Sensing, Vol. 15, pp. 1259-1271.
Doering, E. R. and Basart, J. P., 1991, “Improving the Spatial Resolution of Real-Time Radiography Image Using the Maximum Entropy Method”, Conference Record of the Twenty-Fifth Asilomar Conference on Signals, Systems and Computers, Vol. 2, pp. 1072-1076.
Feng, H., Ercal, F. and Bunyak, F., 1998, “Systolic Algorithm for Processing RLE Image”, IEEE Southwest Symposium on Image Analysis and Interpretation, pp. 127-131.
Finlayson, G. D., Chatterjee, S. S. and Funt, B. V., 1996, “Colour-Texture Inexing”, IEE Colloquium on Intelligent Image Databases , pp. 12/1-12/6.
Healey, C. G. and Enns, J. T., 1998, “Building Perceptual Textures to Visualize Multidimensional Datesets”, Proceedings of Visualization, pp. 111-118.
Heikkinen, J., Klapuri, H. and Saarinen, J., 1996, “Fuzzy Classifier in Detect Diagnosis of Solder Joints”, Proceedings of the Fifth IEEE International Conference, Vol. 1, pp. 113-117.
Hong, J. J., Park, K. J. and Kim, K. G., 1998, “Parallel Processing Machine Vision System for Bare PCB Inspection”, Proceedings of IECON, Vol. 3, pp. 1346-1350.
Jackson, J. C. and Ward, G., 1991, “Surface Inspection of Steel Products Using a Synthetic Aperture Microwave Technique”, British Journal of NDT, Vol. 33, pp. 395-402.
Jumarie, G., 1998, “Entropy of Markovian Processes: Application to Image Entropy in Computer Vision”, Journal of Franklin Institute, Vol. 335, pp. 1327-1338.
Kasari, M. H., Parkkinen, J., Jaaskelainen, T. and Lenz, R., 1996, “Generalized Co-Occurrence Matrix for Multispectral Texture Analysis”, Proceedings of the 13th International Conference on Pattern Recognition, Vol. 2, pp. 785-789.
Kiselman, C. O., 1995, “Regularity Properties of Distance Transformations in Image Analysis”, Computer Vision and Image Understanding, Vol. 64, pp. 390-398.
Kishimoto, S., Kakimori, N., Yamamoto, Y., Takahashi, Y., Harada, T., Iwata, Y., Shigeyama, Y., and Nakao, T., 1990, “A Printed Circuit Board (PCB) Inspection System Employing the Multi-Lighting Optical System”, 8th IEEE/CHMT International IEMT Conference on Electronic Manufacturing Technology Symposium, pp. 120-129.
Ko, K. W. and Cho, H. S., 1998, “Solder Joint Inspection Using Neural Network and Fuzzy Rule-Based Classification”, Proceedings of the 1998 IEEE/RSJ Intelligent Robots and Systems, Vol. 3, pp. 13-17.
Koo, J. H. and Yoo, S. I., 1998, “A Structural Matching for Two-Dimensional Visual Pattern Inspection”, IEEE International Conference on Systems, Man, and Cybernetics, Vol. 5, pp. 4429-4434.
Liu, S. S. and Jernigan, M. E., 1990, “Texture Analysis and Discrimination in Additive Noise”, Computer Vision, Graphics, and Image Processing, Vol. 49, pp. 52-67.
Moganti, M. and Ercal, F., 1996, “Automatic PCB Inspection Algorithm: A Survey”, Computer Vision and Image Understanding, Vol. 63, pp. 287-313.
Muzzolini, R., Yang, Y. H. and Pierson, R., 1994, “Texture Characterization Using Robust Statistics”, Pattern Recognition, Vol. 27, pp. 119-134.
Namuduri, K. -R., Mehrotra, R. and Ranganathan, N., 1994, “Efficient Computation of Gabor Filter Based Multi-Resolution Responses”, Pattern Recognition, Vol. 27, pp. 925-938.
Nikolaidis, N. and Pitas, I., 1995, “Edge Detection Operators for Angular Data”, International Conference on Image Processing, Vol. 2, pp. 157-160.
Ohta, Y. I., Kanade, T. and Sakai, T., 1980, “Color Information for Region Segmentation”, Computer Graphis and Image processing, Vol. 13, pp. 222-241.
Pincus, S., 1995, “Approximate Entropy (ApEn) as a Complexity Measure”, American Institute of Physics, Vol. 5, pp. 110-117.
Schuckers, S. C., 1998, “Approximate Entropy as a Measure of Morphologic Variability for Ventricular Tachycardia and Fibrillation”, Computers in Cardiology, Vol. 25, pp. 265-268.
Seyfullah, H. O. and Levent, O., 1991, “An Automated System for Design-Rule-Based Visual inspection of Printed Circuit Board”, Proceedings of the IEEE International Conference on Robotics and Automation Sacramento, Vol. 3, pp. 2696-2701.
Siew, L. H., Hodgson, R. M. and Wood, E. J., “Texture Measures for Carpet Wear Assessment”, IEEE Trans. Pattern Anal. Mach. Intell., Vol. 10, pp. 92-105.
Teoh, E. K., Mital, D. P., Lee, B. W. and Wee, L. K., 1990, “Automated Visual Inspection of Surface Mount PCBs”, Industrial Electronics Society, IECON ''90., 16th Annual Conference of IEEE, Vol. 1, pp. 576-580.
Thomas, P. W., William, E. H. and Dennis, F. D., 1996, “Efficient Gabor Filter Design for Texture Segmentation”, Pattern Recognition, Vol. 29, pp. 2005-2015.
Trebbia, P. and Bonnet, N., 1990, “EELS Elemental Mapping with Unconventional Methods I. Theoretical Basis: Image Analysis with Multivariate Statistics and Entropy Concepts”, Ultramicroscopy, Vol. 34, pp. 165-178.
Wu, W. Y., Wang, M. J. and Liu, C. M., 1996, “Automated Inspection of Printed Circuit Boards through Machine Vision”, Computers in Industry, Vol. 28, pp. 103-111.
Yu, X. and Yuan, B., 1990, “A New Statistical Texture Feature: Direction Measure”, Proceedings of SPIE - The International Society for Optical Engineering, Vol. 1395, pp. 291-298.
Ye, Q. Z. and Danielsson, P. E., 1988, “Inspection of Printed Circuit Boards by Connectivity Preserving Shrinking”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 10, pp. 737-742.