對自動指紋辨識系統而言，正確的特徵擷取是非常重要的。然而，品質不良影像中的雜訊常會造成特徵擷取錯誤，像是無法正確找出特徵點或是誤判特徵點。為了改善這些現象，目前有很多建立在精確數學模式之上的指紋辨識系統，嘗試解決此一問題，但是都無法適當地處理錯誤的現象。我們都知道，人們對於指紋圖案有極佳的辨識能力，因此，本篇論文運用類似人類思維的方式，應用模糊邏輯與類神經網路，成功地結合模糊理論具有容錯及倒傳遞類神經網路回想速度快之特性，實做具有容錯性且快速的指紋分析比對資料庫系統。每筆指紋資料經模糊化後，再輸入倒傳遞類神經網路訓練後建檔，所耗費的時間約為3秒。指紋資料庫比對每筆樣本平均需時0.08秒。系統在相似度閥值為0.9之情形下，其拒真率為0％，平均讓假率約為0.23％。由以上數據可得知此方法是強健、可靠且快速的。

The correct minutiae extraction is very important in an automatic fingerprint identification system. However, the presence of noise in poor-quality images will cause many extraction faults, such as the dropping of true minutiae and inclusion of false minutiae. Nowadays, most fingerprint identification systems are based on precise mathematical models, but they can not handle such faults properly. As we know, human beings are good at recognizing fingerprint pattern. Therefore, a human-like method is applied. This paper presents an adaptive fuzzy logic and neural network method which is fast and has variable fault tolerance. We implement a fast fingerprint database system with fault tolerance. Before neural network training, every fingerprint is encoded by a fuzzy image encoder. Then the result of training is saved in a database. The training time is 3 seconds. The matching time is 0.08 second. When the threshold is 0.9, the FAR is 0% and FRR is 0.23%. Our experimental results have shown that this fingerprint identification method is robust, reliable and rapid.

目  錄
第一章 緒論……………………………………………1
   1.1 研究動機………………………………………1
   1.2 自動指紋辨識系統……………………………2
   1.3 相關研究………………………………………3
   1.4 論文架構………………………………………5
第二章 指紋影像前處理與分叉點特徵萃取  ………6
   2.1 指紋影像背景知識……………………………7
   2.2 指紋影像前處理與分叉點特徵萃取  …… 10
     2.2.1 正規化   ………………………………12
     2.2.2 Gabor Filter …………………………13
     2.2.3 二值化   ………………………………15
     2.2.4 細線化   ………………………………17
     2.2.5 分叉點的萃取 …………………………21
     2.2.6 後處理   ………………………………23
第三章 模糊影像編碼器 ……………………………25
   3.1 簡介 …………………………………………26
   3.2 模糊影像編碼器實作……………………… 29
第四章 倒傳遞類神經網路 …………………………34
   4.1 簡介 …………………………………………35
   4.2 類神經網路的運作過程…………………… 38
   4.3 倒傳遞類神經網路的演算法……………… 39
   4.4 本研究的網路架構………………………… 43
第五章 自動指紋辨識系統………………………… 46
   5.1 實驗樣本 ……………………………………47
   5.2 系統流程…………………………………… 49
     5.2.1 指紋資料庫訓練流程（模式一） ……49
     5.2.2 指紋資料庫訓練流程（模式二） ……50
     5.2.3 指紋辨認測試流程 ……………………53
   5.3 結果與討論 …………………………………54
     5.3.1指紋影像的旋轉容錯性……………… 54
     5.3.2 指紋影像的位移容錯性 ………………60
     5.3.3 隨機減少特徵點 ………………………64
     5.3.4 模糊影像大小與性能的關係 …………65
     5.3.5 每一指紋影像的處理時間 ……………66
     5.3.6 匹配速度 ………………………………67
     5.3.7 模式二訓練下之可變式的容錯性 ……68
     5.3.8 拒真率 …………………………………71
     5.3.9 認假率 …………………………………72
第六章 結論 …………………………………………73
參考資料………………………………………………74


圖 目 錄

圖 2.1 指紋端點與分叉點示意圖  ………………………………… 7
圖 2.2 指紋細微特徵（點、島、突刺、橋點、短山脊、分叉點）… 9
圖 2.3 指紋細微特徵（端點、交叉點）…………………………… 9
圖 2.4 前處理與分叉點特徵萃取流程圖………………………… 11
圖 2.5 經過Gabor Filter後的指紋影像  ………………………14
圖 2.6 二值化後的指紋影像 ……………………………………  16
圖 2.7 細線化後的指紋影像 …… …………………………………17
圖 2.8 細線化演算法採用之視窗  …………………………………18
圖 2.9  舉例說明 ……………………………………………19
圖 2.10 利用 函數分辨端點與分叉點………………………… 22
圖 2.11 指紋影像處理後得到的結果…………………………………24
圖 3.1 吊鐘型歸屬函數………………………………………………28
圖 3.2 傳統一維模糊集合……………………………………………28
圖 3.3 影像分成64（8x8）個格子………………………………… 31
圖 3.4 二維模糊化歸屬函數 ……………………………………… 32
圖 3.5 歸屬函數參數示意圖……………………………………… 32
圖 3.6 指紋分叉點的模糊影像…………………………………… 33
圖 4.1 雙彎曲函數 ………………………………………………… 37
圖 4.2三層倒傳遞類神經網路架構圖……………………………40
圖 4.3 倒傳遞類神經網路架構………………………………………45
圖 5.1 自動指紋辨識系統操作介面 ……………………………… 48
圖 5.2 指紋資料庫訓練流程（模式一）……………………………51
圖 5.3指紋資料庫訓練流程（模式二）……………………………52
圖 5.4 指紋辨認測試流程……………………………………………53
圖 5.5 萃取出的分叉點與原始指紋影像的對照圖 ……………… 55
圖 5.6 原始影像經模糊化後的特徵影像……………………………55
圖 5.7 將萃取出之分叉點指紋影像順時針旋轉5∘… … ……  57
圖 5.8 將原始影像經模糊化後的特徵影像，順時針旋轉5∘後所得  到的模糊影像   …………………………………………  57
圖 5.9 指紋旋轉對系統的影響………………………………………59
圖 5.10 由水平方向位移指紋對系統的影響……………………  61
圖 5.11由垂直方向位移指紋對系統的影響 ………………………61
圖 5.12 由任意方向位移指紋對系統的影響  ……………………62
圖 5.13 隨機減少分叉點的辨識結果………………………………64
圖 5.14模式二訓練下之可變式的容錯性 …………………………69


表   目   錄

表 5.1 特徵影像所對應的數值…………………… 56
表5.2特徵影像順時鐘旋轉5∘後所對應的數值 …
       …………………………………………… 58
表 5.3 同時旋轉與任意方向位移的容錯範圍…… 63
表 5.4 模糊影像大小與性能的關係……………… 65
 表 5.5 模式二訓練下可變式之容錯性的時間成本與
 FAR值……………………………………… 70

參考資料

[1]	Bebis G., Deaconu T., Georgiopoulos M., “Fingerprint Identification Using Delaunay Triangulation”, Information Intelligence and System, 1999 International Conference on, Pages:452-459, 31 Oct.-3 Nov. 1999.
[2]	L. O’Gorman and J. V. Nickerson, “An Approach to Fingerprint Filter Design” , Pattern Recognition, Vol. 22, No. 1, Pages. 29-38, 1989.
[3]	B. G. Sherlock, D. M. Monro and K. Millard, “Fingerprint Enhancement by Directional Fourier Filtering”, IEEE Proc. Vis. Image Signal Processing Vol. 14, No. 2, Pages. 87-94, 1994.
[4]	L.Coetzee and E.C. Botha, “Fingerprint Recognition in Low Quality Images”, Pattern Recognition, Vol. 26, No. 10, Pages. 1441-1460, 1993.
[5]	Moayer, B. and Fu, K.S., “A Tree System Approach for Fingerprint Recognition”, IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 9, No. 3, Pages. 376-387, 1986.
[6]	B. M. Mehtre, “Fingerprint Image Analysis for Automatic Identification”, Machine Vision and Applications, Vol. 6, Pages. 124-139, 1993.
[7]	B. M. Mehtre, N. N. Murthy, S. Kapoor, “Segmentation of Fingerprint Images Using the Direction Image ”, Pattern Recognition, Vol. 20, No. 4, Pages. 429-435, 1987.
[8]	R. M. Stock and C. W. Swonger, “Development and Evaluation of a Reader of Fingerprint Minutiae ”, Cornell aeronautical Laboratory, Technical Report CAL No. XM-2478-X-1, Pages. 13-17, 1969.
[9]	C. L. Wilison, G. T. Candelda and c. I. Watson, “Neural Network Fingerprint Classification”, J. Artific. Neural Networks Vol. 1, No. 2, Pages.1-25, 1993.
[10]	A. R. Rao, “A Taxonomy for Texture Description and Identification”, New York: Springer-Verlag, 1990.
[11]	A. Jain, L. Hong and R. Bolle, “On-Line Fingerprint Verification”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 19, No. 4,  Pages. 302-314, April 1997.
[12]	Zs. M. Kovacs Vajian*, R. Rovatti, M. Frazzoni, “Fingerprint Ridge Distance Computation Methodologies”, Pattern Recognition, Vol. 33, Pages. 69-80, 2000.
[13]	D. Maio and D. Maltoni, “Direction Gray-Scale Minutiae detection in Fingerprints”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 19, No. 1, Pages. 27-40, January 1997.
[14]	M. Kawagoc and A. Tojo, “Fingerprint Pattern Classification”, Pattern Recognition, Vol. 17, No. 3, Pages. 295-303, 1984.
[15]	V. S. Srinvasan and N. N. Murthy, “Detection of Singular Point in Fingerprint Image”, Pattern Recognition, Vol. 25, No. 2,  Pages. 139-153, 1992.
[16]	Anil, K Jain and K. Karu, “Fingerprint Classification”, Pattern Recognition, Vol. 29, No. 3, Pages. 389-404, 1996.
[17]	B. Moayer and K. S. Fu, “A Syntactic Approach to Fingerprint Pattern Recognition”, Pattern Recognition, Vol. 7, Pages. 1-23, 1975.
[18]	K. Rao and K. Black, “Type Classification of Fingerprints: A Syntactic Approach”, IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. PAMI-2, No. 3, May 1980.
[19]	F. Tou, Y. Q. Shi and P. Engler, “Fingerprint Pattern Recognition for Medical Uses-A Frequency Domain approach”, Proceeding of The 1993 IEEE Nineteenth Annual Northeast Bioengineering Conference, Pages. 176-177, 1993.
[20]	A. P. Fitz and R. J. Green, “Fingerprint Classification Using a Hexagonal Fast Fourier Transform”, Pattern Recognition, Vol. 29, No. 10, Pages. 1587-1597, 1996.
[21]	A. K. Hrechak and J. A. Mchugh, “Automated Fingerprint Recognition Using Structural Matching”, Pattern Recognition, Vol. 23, No. 8, Pages. 893-904, 1990.
[22]	Salil Prabhakar, Anil K. Jain, Jianguo Wang, Sharath Pankanti & Ruud  Bolle. “Minutia Verification and Classification for Fingerprint Matching,” 15th International Conference on, Pages: 25-29, Volume: 1, 3-7 Sept. IEEE 2000.
[23]	C.L. Wilson, G. T. Candela, C. I. Watson, “Neural Network fingerprint Classification” J. Artificial Neural Networks, Vol. 1, Pages: 203-228, 1993.
[24]	K. Hrechak, and J. A. McHugh, “Automated Fingerprint Recognition Using Structural Matching,” Pattern Recognition, Vol. 23, Pages. 893-904, 1990.
[25]	R.E. Henry, “Classification and Uses of Fingerprints” London : Routledge, 1990.
[26]	J. S. Lim, “Two-Dimensional Signal and Image Processing” , Prentice Hall, Inc., Pages. 496, 1990.
[27]	Lin Hong, Yifei Wan, and Anil Jain, Fellow, “Fingerprint Image Enhancement：Algorithm and Performance Evaluation,” IEEE Transaction on Pttern Analysis and Machine Intelligence, Vol.20, No.8, August 1998.
[28]	A. K. Jain, S. Prabhakar, L. Hong, and S. Pankanti, “Filterbank-Based Fingerprint Matching,” IEEE Transactions on Image Processing, Vol.9, No.5, pp.846-859, May 2000.
[29]	Mohamed Suliman M and Henry O Nyongesa, “Automatic Fingerprint Classification System Using Fuzzy Neural Techniques” IEEE International Conference on, Vol. 1, 12-17, May 2002.
[30]	F. W. M. Steniford and R. G. Mortimer, “Some New Heurisitics for Thinning Binary Handprinted Characters for OCR” IEEE Transactions on System, Vol. 13, No.1, Pages. 81-84, January~February 1983.
[31]	S. Zhang and K. S. Fu, “A Thinning Algorithm for Discrete Binary Images” Proc. ICCA’84, Inc. Conference on Computers and Applications, Beijing, Pages.879-886, 1984.
[32]	C M. Holt, A. Steward, M. Clint and R. H. Perrott, “An Improved Parallel Thinning  Algorithm”, Communications of ACM. Vol. 30, No.2, Pages. 156-160, 1987.
[33]	Qun Gao, Philipp Forster; “Fingerprint recognition Using CNNS: Fingerprint Preprocessing”IEEE 2001.
[34]	D. Simon-Zorita, J. Ortega-Garcia, S.;“Minutiae Extraction Scheme for Fingerprint Recognition Systems”IEE 2001.
[35]	D. Simon-Zorita, J. Ortega-Garcia, S.;“Minutiae Extraction Scheme for Fingerprint Recognition Systems”IEE 2001.
[36]	Haiping Lu, Xudong Jiang and Wei-Yun Yau, “Effective and Efficient Fingerprint Image Post-processing” 7th International Conference on Control, ICARCV’02, Dec. 2002.
[37]	S. Kasaei, M. Deriche, and B. Boashash, “Fingerprint Feature Extraction Using Block-Direction on Reconstructed Images” Speech and Image Technologies for Computing and Telecommunications, IEEE TENCON 1997.
[38]	蘇木春、張孝德, “機器學習：類神經網路、模糊系統以及基因演演算法則”, 全華科技圖書.
[39]	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, 2003.
[40]	蔡英男，“應用影像處理與類神經網路於偏光膜瑕疵辨識”台灣科技大學，高分子工程系.