臺灣博碩士論文加值系統

近年來，由於傳統身份辨識方法的諸多問題，使得利用個人生物特徵來辨識身份的技術
逐漸受到重視。由於虹膜辨識技術有良好的便利性與辨識率，使其在眾多的生物辨識技
術當中脫穎而出，廣為使用。傳統的虹膜辨識系統均是假設使用者在正視攝影機的情況
下擷取虹膜影像，然而此項假設會限制住虹膜辨識的應用範圍。本論文將深入探討使用
在非正向的情形下所攝得之虹膜來辨識個人身份的技術。本研究的目標有二：一為利用
即有的硬體架構取得不同視角的近紅外光與可見光彩色的四頻譜虹膜影像，並且改良舊
有系統中虹膜影像品質評估的方法，對虹膜定位與特徵比對的部份做最佳化，使得系統
能夠快速的進行辨識，並且依舊擁有良好的辨識率。二為驗証仿射矯正 (Affine
Rectification) 是否適用於將非正向的虹膜影像轉換為正向視角的虹膜影像。實驗結
果顯示，改進後的系統不但有較高的效率，也具有較好的辨識效果。

In recent years, techniques for personal identification with biometrics have
drawn more and more attention from people due to the insecurity of the
traditional authentication methods. Because of the convenience and high
recognition accuracy, iris recognition techniques have stood out among the
biometric personal identification techniques and are widely adopted in many
applications. Most of the existing iris recognition systems are developed
under the assumption that the iris images are acquired with the orthogonal
view imaging condition (OVIC). This assumption has restricted the
applicability of iris recognition systems. In this thesis, we will discuss
in depth an iris recognition technique that considers the non-orthogonal
view iris image for personal identification. The purpose of this study is
twofold. The first is to improve the iris image quality assessment method
and to optimize the iris localization and classification process of our
pervious four-spectral iris recognition system. The second is to verify
whether the affine rectification is appropriate to convert a non-orthogonal
view iris image into an orthogonal view image. Experiments show that the
improved system has higher efficiency and better recognition accuracy.

1 簡介. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.1 動機與目的. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.2 文獻探討. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
1.3 系統流程. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
1.4 研究成果. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
1.5 章節架構. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2 虹膜取像硬體架構8
2.1 硬體架構簡介. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
2.2 雙CCD 取像模組. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.3 雙CCD 攝影機影像校正. . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3 虹膜影像品質評估. . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3.1 瞳孔定位. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3.2 清晰度測量. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
3.3 動態模糊偵測. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4 虹膜定位與特徵萃取21
4.1 仿射矯正. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
4.2 虹膜定位. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
4.3 眼瞼定位. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
4.4 虹膜影像正規化. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
4.5 特徵萃取. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
4.6 虹膜碼比對. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
5 仿射矯正影像分析. . . . . . . . . . . . . . . . . . . . . . . . . . . . 33
5.1 虹膜特徵成像模擬. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33
5.1.1 簡化眼球光學膜型. . . . . . . . . . . . . . . . . . . . . . . . . . . 33
5.1.2 無失真攝影機模型. . . . . . . . . . . . . . . . . . . . . . . . . . . 34
5.1.3 虹膜特徵在不同角度間成像位移分析. . . . . . . . . . . . . . . . . 36
5.2 真實虹膜影像特徵位移量之計算. . . . . . . . . . . . . . . . . . . . . . . . 37
6 實驗結果. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44
6.1 虹膜定位. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44
6.2 系統速度. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48
6.2.1 影像品質評估. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48
6.2.2 特徵萃取. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 50
6.2.3 分類. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 50
6.2.4 總結. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 50
6.3 仿射矯正影像分析. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51
7 結論與未來展望. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54
7.1 結論. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54
7.2 未來展望. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54

[1] 吳庭榕. 多視角虹膜辨識系統. 國立暨南國際大學資訊工程學系, 2005.
[2] 林秩群. 非正向視角虹膜辨識系統. 國立暨南國際大學資訊工程學系, 2006.
[3] John Daugman. High Confidence Visual Recognition of Persons by A Test of Statistical
Independence. IEEE Trans. Pattern Anal. Machine Intell., 15(11):1148–
1161, 1993.
[4] Richard Patrick Wildes. Iris Recognition: An Emerging Biometric Technology.
Proceedings of the IEEE, 85(9):1348–1363, 1997.
[5] John Daugman and Cathryn Downing. Recognizing Iris Texture by Phase Demodulation.
IEE Colloquium on Image Processing for Biometric Measurement,
(2):1–8, 1994.
[6] John Daugman. Biometric Personal Identification System Based on Iris Analysis.
United States Patent, Patent Number: 5291560, IriScan Inc., 1994.
[7] John Daugman. The Importance of Being random: Statistical Principles of Iirs
Recognition. Pattern Recognition, 36(2):279–291, 2001.
[8] John Dangman and Cathryn Downing. Epigenetic Randomness, Complexity and
Sigularity of Human Iris Patterns. In Proceedings of the Royal Society, B. 268,
Biological Sciences, pages 1737–1740, 2001.
[9] Richard Patrick Wildes, Jane Circle Asmuth, G. L. Green, Stephen Charles Hsu,
Raymond Joseph Kolczynski, James Regis Matey, and Sterling Eduard McBride.
A System for Automated Iris Recognition. In Proceedings of the Second IEEE
Workshop on Applications of Computer Vision, pages 121–128, 1994.
[10] Richard Patrick Wildes, Jane Circle Asmuth, Keith James Hanna, Stephen Charles
Hsu, Raymond Joseph Kolczynski, James Regis Matey, and Sterling Eduard
McBride. Automated, Non-Invasive Iris Recognition System and Method. United
States Patent, Patent Number: 5572596, David Sarnoff Research Center, Inc.,
1996.
[11] Libor Masek and Peter Kovesi. Recognition of Human Iris Patterns for Biometric
Identification. The School of Computer Science and Software Engineering, The
University of Western Australia, 2003.
[12] Wageeh Boles and Boualem Boashash. A Human Identification Technique Using
Images of the Iris And Wavelet Transform. IEEE Trans. on Signal Processing,
46(4):1185–1198, 1998.
[13] Christel lo‥?c Tisse, Lionel Martin, Lionel Torres, and Michel Robert. Person Identification
Technique Using Human Iris Recognition. In Proceedings of International
Conference on Vision Interface, pages 294–299, 2002.
[14] Ruth Gaunt, Bradford Bonney, Robert Ives, Delores Etter, and Robert Schultz.
Collection and Segmentation of Non-orthogonal Irises for Iris Recognition. In
Proceedings of the Biometric Consortium Conference, 2005.
[15] Bradford Bonney, Robert Ives, Delores Etter, and Yingzi Du. Iris Pattern Extraction
Using Bit-Plane Analysis. In Proceedings of the IEEE 38th Annual Asilomar
Conference on Signals, Systems, and Computers, volume 1, pages 582–586, 2004.
[16] Aditya Abhyankar, Lawrence Hornak, and Stephanie Schuckers. Off-angle Iris
Recognition Using Bi-orthogonal Wavelet Network System. In Proceedings of the
IEEE Workshop on Automatic Identification Advanced Technologies, pages 239–
244, 2005.
[17] Vivekanand Dorairaj, Natalia A. Schmid, and Gamal Fahmy. Performance Evaluation
of Non-ideal Iris Based Recognition System Implementing Global ICA Encoding.
In Proceedings of the IEEE International Conference on Image Processing,
volume 3, pages 285–288, 2005.
[18] Christopher Boyce, Arun Ross, Matthew Monaco, Lawrence Hornak, and Xin Li.
Multispectral Iris Analysis: A Preliminary Study51. In Proceedings of the 2006
Conference on Computer Vision and Pattern Recognition Workshop, 2006.
[19] Andrew Fitzgibbon, Maurizio Pilu, and Robert Fisher. Direct Least Square Fitting
of Ellipse. IEEE Trans. Pattern Anal. Machine Intell., 21(5):476–480, 1999.
[20] Kang Ryoung Park and Jaihie Kim. A Real-Time Focusing Algorithm for Iris
Recognition Camera. IEEE Trans. Syst., Man, Cybern., 35(3):441–444, 2005.
[21] Kang Ryoung Park. System of the Real-Time Acquisition and Recognition for Iris
Images. IEICE Transactions on Fundamentals of Electronics, Communications
and Computer Sciences, 88-a(9):2436–2445, 2005.
[22] John Canny. A Computational Approach to Edge Detection. IEEE Trans. Pattern
Anal. Machine Intell., 8(6):679–698, 1986.
[23] Rong-En Fan, Pai-Hsuen Chen, and Pai-Hsuen Chen. Working Set Selection Using
Second Order Information for Training SVM. Journal of Machine Learning
Research, 6:1889–1918, 2005.
[24] Martin Fischler and Robert Bolles. Random Sample Consensus, A Paradigm for
Model Fitting with Applications to Image Analysis and Automated Cartography.
Communications of the ACM, 24(6):381–395, 1981.
[25] John Daugman. How Iris Recognition Works. IEEE Trans. on Circuits and Systems
for Video Technology, 14(1):21–30, 2004.
[26] Chia-Te Chou, Sheng-Wen Shih, Wen-Shiung Chen, and Victor W. Cheng. Iris
Recognition with Multi-Scale Edge-Type Matching. In Proceedings of the IAPR
International Conference on Pattern Recognition, volume 4, pages 545–548, 2006.
[27] Hong Hua, Prasanna Krishnaswamy, Jannick, and Rolland. Video-based eyetracking
methods and algorithoms in head-mounted displays. Optics Express,
14(10):4328–4350, 2006.
[28] Cohen Paul Weng, Juyang and Marc Herniou. Camera calibration with distortion
models and accuracy evaluation. IEEE Trans. Pattern Anal. Machine Intell.,
14(10):965–980, 1992.
[29] Les Piegl. On NURBS: a survey. IEEE Computer Graphics and Application,
11(1):55–71, 1991.
[30] Philippe Lavoie. The nurbs++ library.