臺灣博碩士論文加值系統

隨著科技的進步，製造偽鈔的手法也越來越逼真，現今的各種鈔票防偽設計皆一一被破解，一般民眾及商家使用市售的簡單檢驗工具，例如驗鈔筆、紫外光燈管已不敷使用，因此如何準確的檢出偽鈔使其無所遁形，便成為當下重要的課題。我們將發展一套新的以機器視覺為基礎的偽鈔辨識機，改善現有的偽鈔辨識機制。
早期以機器視覺為基礎的鈔票辨識系統皆以類神經網路為辨識核心，且對於鈔票之特徵描述皆無詳細的研究探討，然而類神經網路的架構存在許多問題，本論文擬針對國內新台幣紙鈔的紋理特性，結合簡單的背光設備作詳細紋理特徵的分析，包含色彩紋理、灰階紋理與空間結構特徵，並提出PCA可變樣板比對之演算法檢測鈔票，搭配擁有強大學習能力的SVM辨識鈔票的真偽，改善類神經網路結果為區域最小解的風險，實作一套即時的自動光學偽鈔辨識系統，提高以機器視覺為基礎的偽鈔辨識系統辨識率與效率。

With the advance in technology, the method of making counterfeit banknote is getting more and more sophisticated that leads to the failure of many banknotes detectors, such as banknote verification pen and ultraviolet tube that ordinary people and stores use. Therefore, the problem on how to detect counterfeit banknotes correctly has become an important issue. We will develop a new counterfeit banknote recognition system based on machine vision to alleviate the current technologies.
In the early years, machine learning based banknote recognition systems are based on neural network, and researches on the description of features for banknotes have not been fully discussed. This study proposes an analysis method according to the texture features of NT banknotes in combination with simple backlight device, inclusive of color texture, grayscale texture and spatial structure features, and use PCA variable template matching algorithm to do banknote detection. Unlike NN which may converge to a local minimum, our method implements a real-time automatic optical counterfeit banknote recognition system which is machine vision based to increase the recognition rate and performance.

英文摘要.....................................................................I
中文摘要....................................................................II
誌 謝...................................................................III
目 錄....................................................................IV
圖表索引....................................................................VI
第一章 緒論.................................................................1
1.1 研究背景與動機......................................................1
1.2 相關文獻探討........................................................6
1.3 研究方法............................................................9
1.4 論文架構...........................................................10
第二章 基礎理論............................................................11
2.1 紋理分析...........................................................11
2.1.1 灰階共生矩陣..................................................12
2.1.2 鄰近灰階相依矩陣..............................................15
2.2 主量分析...........................................................20
2.3 支撐向量機.........................................................26
2.3.1 線性支撐向量機................................................26
2.3.2 非線性支撐向量機..............................................32
2.3.3 支撐向量機參數模型之正確率評估................................35
2.3.4 多類支撐向量機................................................36
第三章 偽鈔辨識系統架構....................................................39
3.1 系統流程...........................................................39
3.2 硬體平台設備.......................................................41
3.3 物件切割...........................................................42
3.4 影像前處理.........................................................46
3.5 PCA可變樣板檢測....................................................50
3.6 特徵擷取...........................................................53
3.6.1 視窗安全線與浮水印之空間特徵..................................54
3.6.2 視窗安全線與浮水印之紋理特徵..................................58
3.6.3 特徵擷取流程圖................................................60
第四章 實驗結果............................................................61
4.1 特徵擷取實驗結果與討論.............................................64
4.1.1 各種輸入之情況................................................64
4.1.2 真偽鈔特徵之比較..............................................74
4.2 支撐向量機辨識器實驗結果與討論.....................................77
4.2.1 支撐向量機核函數與其參數之選擇................................77
4.2.2 使用階段實驗結果..............................................82
4.3 實驗結果討論.......................................................88
第五章 結論與未來研究方向..................................................90
5.1 結論...............................................................90
5.2 未來研究方向.......................................................91
參考文獻....................................................................92

[1]陳偉民, "生活科學家-我有真鈔," 遠哲發現月刊46期, 2000.
[2]蔡宜壽, "發光纖維的製造與應用," 絲織園地季刊44期, 2003.
[3]吳湘匡, "我國的防偽印刷技術," 印藝183期, 2000.
[4]M. Fischetti, "驗鈔機如何認出假鈔？," 科學人72期2月號, 2008.
[5]中央銀行全球資訊網 http://www.cbc.gov.tw/
[6]缽村健, 小笠原治, "新紙鈔防偽技術," 牛頓258期, 2005, 108-113頁.
[7]林源同, "鈔券及其他有價證券、安全性文件用紙之品質檢驗與管理研習," 中央印製廠報告, 2008.
[8]曲文豪, "防偽印製技術淺談," 世新大學圖文傳播暨數位出版學系, 2007, 第24-117頁.
[9]F. Takeda, S. Omatu, and S. Onami, "Recognition system of US dollars using a neural network with random masks," Proceedings of 1993 International Joint Conference on Neural Network, vol.2, pp. 2033-2036, 1993.
[10]F. Takeda and T. Nishikage, "Multiple kinds of paper currency recognition using neural network and application for Euro currency," Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Network, vol.2, pp. 143-147, 2000.
[11]F. Takeda, L. Sakoobunthu, and H. Satou, "Thai banknote recognition using neural network and continues learning by DSP unit," Knowledge-Based Intelligent Information and Engineering Systems, pp. 1169-1177, 2003.

[12]張亨菖, "多國真偽鈔辨識系統商品化之研究," 國立高雄第一科技大學電腦與通訊工程所碩士論文, 2003.
[13]江惠玲, "真偽鈔辨識系統之軟體設計," 國立高雄第一科技大學電腦與通訊工程所碩士論文, 2004.
[14]洪啟智, "真偽鈔辨識系統之硬體設計," 國立高雄第一科技大學電腦與通訊工程所碩士論文, 2004.
[15]A. Frosini, M. Gori, and P. Priami, "A neural network-based model for paper currency recognition and verification," IEEE Transactions on Neural Networks, vol. 7, pp. 1482-1490, 1996.
[16]L. Jae-Kang and K. Il-Hwan, "New recognition algorithm for various kinds of Euro banknotes," Proceedings of the 29th Annual Conference of the IEEE Industrial Electronics, vol.3, pp. 2266-2270, 2003.
[17]A. Ahmadi, S. Omatu, and M. Yoshioka, "Implementing a reliable neuro-classifier for paper currency using PCA algorithm," Proceedings of the 41st SICE Annual Conference of the Society of Instrument and Control Engineers, vol.4, pp. 2466-2468, 2002.
[18]M. Sevkli, A. Türkyilmaz, and M. S. Aksoy, "Banknote recognition using inductive learning," International Conference on Fuzzy Systems and Soft Computational Intellingnce in Management and Industrial Engineering, 2002.
[19]Q. Ji, Q. Dongping, and Z. Mengjie, "A digit recognition system for paper currency identification based on virtual instruments," Proceedings of the International Conference on Information Acquisition and Automation, pp. 228-233, 2006.
[20]C. He, M. Girolami, and G. Ross, "Employing optimized combinations of one-class classifiers for automated currency validation," Pattern Recognition, vol. 37, pp. 1085-1096, 2004.

[21]M. Ionescu and A. Ralescu, "Fuzzy Hamming distance based banknote validator," The 14th IEEE International Conference on Fuzzy Systems, pp. 300-305, 2005.
[22]蘇文彬, "應用多核心支援向量基於偽鈔辨識," 國立中山大學電機工程所碩士論文, 2008.
[23]C. Herley, P. Vora, and S. Yang, "Detection and deterrence of counterfeiting of valuable documents,"2004 International Conference on Image Processing, Vol. 4, pp. 2423-2426, 2004.
[24]江雅雯, "值基於色彩及紋理分析之鈔票偵測系統," 私立中原大學資訊工程所碩士論文, 2006.
[25]黃識峰, "鈔劵防偽瑕疵之光學檢測," 國立台北科技大學自動化科技研究所碩士論文, 2007.
[26]吳明川, 林哲宇, and 卓文財, "鈔券印刷瑕疵檢測系統之開發," 2008 數位科技與創新管理研討會, 2008.
[27]Vapnik, V.N., "The nature of statistical learning theory," Springer, New York, 1995.
[28]R. M. Haralick, K. Shanmugam, and I. H. Dinstein, "Textural features for image classification," IEEE Transactions on Systems, Man and Cybernetics, vol. 3, pp. 610-621, 1973.
[29]C. Sun and W. G. Wee, "Neighboring gray level dependence matrix for texture classification," Computer Vision, Graphics, and Image Processing, vol. 23, pp. 341-352, 1983.
[30]T. Van Gestel, B. Baesens, J. Suykens, M. Espinoza, D. E. Baestaens, J. Vanthienen, and B. De Moor, "Bankruptcy prediction with least squares support vector machine classifiers," 2003 IEEE International Conference on Computational Intelligence for Financial Engineering, pp. 1-8, 2003.
[31]S.-T. Chen and P.-S. Yu, "Pruning of support vector networks on flood forecasting," Journal of Hydrology, vol. 347, pp. 67-78, 2007.
[32]Y. B. Dibike, S. Velickov, D. Solomatine, and M. B. Abbott, "Model induction with support vector machines: introduction and applications," Journal of Computing in Civil Engineering, vol. 15, pp. 208-216, 2001.
[33]Yang, Y. & Liu, X., "A re-examination of text categorization methods, " Proceedings of the 22nd annual international ACM Special Interest Group on Information Retrieval conference on Research and Development in Information Retrieval, pp. 42-49, 1999.
[34]林卓彥, "自動分類方法之比較," 國立中正大學資訊工程研究所碩士論文, 2005.
[35]K. Pearaon, "On lines and planes of closest fit to systems of points in space," Philosophical Magazine, vol1.2, pp.559-572, 1901.
[36]H. Hotelling, "Analysis of a complex of statistical variables into principal components," Journal of Educational Psychology, vol.24, pp. 498-520, 1933.
[37]M. Turk, and A. Pentland, "Eigenfaces for recognition," Journal of Cognitive Neuroscience vol. 3, pp. 71-86, 1991.
[38]R. Fletcher, "Practical Methods of Optimization," John Wiley and Sons, Inc., 2nd edition, 1987.
[39]E. B. Bernhard, M. G. Isabelle, and N. V. Vladimir, "A training algorithm for optimal margin classifiers," Proceedings of the fifth Annual Workshop on Computational Learning Theory Pittsburgh, Pennsylvania, United States: ACM, 1992.
[40]A. Kumar and G. K. H. Pang, "Defect detection in textured materials using Gabor filters," IEEE Transactions on Industry Applications, vol. 38, pp. 425-440, 2002.
[41]R. Jae-Seung, O. Jong-Hwan, K. Jeong-Goo, K. Tak-Mo, and P. Kil-Houm, "TFT-LCD panel Blob-Mura inspection using the correlation of wavelet coefficients," TENCON 2004：2004 IEEE Region 10 Conference, vol. 1, pp. 219-222, 2004.
[42]Y. Han and P. Shi, "An adaptive level-selecting wavelet transform for texture defect detection," Image and Vision Computing, vol. 25, pp. 1239-1248, 2007.
[43]W.B. Frakes, R. Baeza-Yates, and B.Y. Ricardo, Information Retrieval: Data Structures and Algorithms, Prentice-Hall, 1992.
[44]C. Chin Chen, Y. Tai Xing, and Y. Hsuan Yen, "Paper Currency Verification with Support Vector Machines," Third International IEEE Conference on Signal-Image Technologies and Internet-Based System, pp. 860-865, 2007.