隨著社會經濟的發展，人們對於安全的問題越來越重視，生物辨識為近年來非常熱門的研究題目，而其中針對虹膜所發展出來的生物辨識技術因為其高穩定度以及唯一性，也越來越受到大家的重視，出現很多相關的學術研究主題。
本論文提出了一個高效能的虹膜辨識系統，系統架構主要分為三個部份：影像前置處理、虹膜特徵提取以及特徵比對。輸入的人眼影像首先經過前置處理以及影像處理技術取得所需之虹膜部分；針對特徵提取的部分我們利用了小波轉換以及判別分析(Discriminant Analysis)中LDA(Linear Discriminant Analysis)、DLDA(Direct Linear Discriminant Analysis)、DF-LDA(Direct Fractional-step Linear Discriminant Analysis)三種方法將影像投射至表現最佳化特徵的子空間，除了達到將資料降維的功能，更取得最能代表使用者身份的虹膜特徵；特徵比對的部份，利用支援向量機(Support Vector Machine)對虹膜資料庫中每個類別訓練產生模型，進而比對不同類別的虹膜影像。
我們利用CASIA虹膜影像資料庫以及自行建置的虹膜影像資料庫來做實驗。CASIA資料庫計有108人，其中107人用來訓練虹膜辨識系統，剩下的1人作為入侵測試。實驗的結果，錯誤拒絕率為0.0838%，錯誤接受率為0.68%。自行建置之資料庫計有108人，其中107人用來訓練虹膜辨識系統，剩下的1人作為入侵測試。實驗的結果，錯誤拒絕率為0.12%，錯誤接受率為2.03%。和現有的系統比較，本論文提出的方法相當的有效和可行。

With the progress of social and economical development, people are being increasingly concerned over the issue of security, resulting in the recent popularity of biometric as the research topic. Among all the biometric related techniques, the one that targets iris recognition stands out for its great stability and uniqueness. Iris recognition technique has got much attentions from public and created many related topics for academic researches.
This paper aims to present a highly effective iris recognition system whose frame consists of three main parts: image preprocessing, feature extraction, and feature matching. Firstly, the captured images of human eyes were undertook the techniques of preprocessing and image processing in order to obtain the request iris segments. In the feature extraction stage, we applied the wavelet transform technique and three methods of Discriminant Analysis, namely, LDA(Linear Discriminant Analysis), DLDA(Direct Linear Discriminant Analysis), and DF-LDA (Direct Fractional-step Linear Discriminant Analysis), to project the images to the subclass where the most important features were included. Based on the mapped subclass, the dimensionality can be reduced but the most discriminating iris features of the users can be extracted. For the final stage, we made use of the Support Vector Machine to train each individual class derived from the iris database, and to create the model for future matching for each individual class.
We use CASIA iris database and database built by ourselves for testing purpose. There are 108 people in CASIA iris database. We use 107 people to train the iris recognition system; the remaining 1 people to intrude the system. The experimental results show that the false accept rate is 0.084% and the false rejection rate is 0.68%. There are 108 people in database built by ourselves. We use 107 people to train the iris recognition system; the remaining 1 people to intrude the system. The experimental results show that the false accept rate is 0.12% and the false rejection rate is 2.03%.Compared to other existing research results, the proposed method is quite effective and practical.

[1] Chen Wen-Shiung, Yuan Shang-Yuan, ”A novel Personal Biometric Authentication Technique Using Human Iris Based on Fractal Dimension Features”, Proceedings of the International Conference on Acoustics, Speech and Signal Processing.(2003)
[2] Christel-Loic Tisse, Lionel Torres, Michel Robert, ”Person Identification Technique Using Human Iris Recognition”, The 15th International Conference on Vision Interface,Calgary,Canada, pp.294-300. (2002)
[3] Chia-Te Chu, Ching-Han Chen, “High Performance Iris Recognition Based on LDA and LPCC”, Proceedings of the 17th IEEE International Conference on Tools with Artificial Intelligence.(2005)
[4] Daugman J, “High Confidence Visual recognition of persons by a test of statistical independence”[J], IEEE Transaction on Pattern Analysis and Machine Intelligence, pp.1148-1161. (1993)
[5] Daugman J, “Recognition People by their Iris Pattern”, Information Security Technical Report, Vol.3, No.1, pp.33-39. (1998)
[6] D. Swets, J. Weng, “Using discriminant eigenfeatures for image retrieval” , IEEE Transaction on Pattern Analysis and Machine Intelligence, pp.831-836. (1996)
[7] Erik RYDGREN, Thomas EA, “Iris Features Extraction Using Wavelet Packets”, International Conference on Image Processing , pp.861-864. (2004)
[8] Hui Kong, Xuchun Li, Matthew Turk, Chandra Kambhamettu, “Discriminant Subspace Analysis for Face Recognition with Small Number of Training”, IEEE Transactions on System, Man and Cybernetics, Part B.
[9] H. Yu and J. Yang, “A direct LDA algorithm for high-dimensional data with application to face recognition,” Pattern Recognition, Vol.34, pp.2067-2070, (2001)
[10] Juwei Lu, K. N. Plataniotis, A. N. Venetsanopoulos, “Face Recognition Using LDA-Based Algorithms[J]”, IEEE Transactions on Neural Networks, Vol.14, No.1.(2003)
[11] Joachims T (2000) SVMlight is an implementation of Support Vector Machines (SVMs) in C. http://ais.gmd.de/~thorsten/svm_light. University of Dortmund. Collaborative Research Center on “Complexity Reduction in Multivariate Data”(SFB475).
[12] Joachims T (1998) Making Large-Scale SVM Learning Practical. LS8-Report, University of Dortmund, LS VIII-Report.
[13] Joachims T (2000) Estimating the Generalization Performance of a SVM Efficiently. Proceedings of the International Conference on Machine Learning, Morgan Kaufman.
[14] J. D. Woodward, ”Biometrics：privacy’s foe or privacy’s friend?”, Proceedings Of the IEEE, Vol.85, No.9, pp.1480-1492.(1997)
[15] K. Liu, Y. Q. Cheng, J. Y. Yang and X. Liu,” An efficient algorithm for Foley-Sammon optimal set of discriminant vectors by algebraic method[J]”, International Journal of Pattern Recognition and Artificial Intelligence, Vol.6, pp.817-829.(1992)
[16] Li Ma, Tieniu Tan, ”Personal Identification Based on Iris Texture Analysis”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.25, No.12. (2003)
[17] Li Ma, Yunhong Wang, Tieniu Tan, “Iris Recognition Based on Multichannel Gabor Filtering”, Proceedings of the Fifth Asian Conference on Computer Vision, Vol.1, pp.279-283. (2002)
[18] L. Chen, H. Liao, M. Ko, J. Lin, G. Yu, ”A new LDA-based face recognition system which can solve the small sample size problem”, Pattern Recognition, Vol.33, No.10, pp.1713-1726. (2000)
[19] Mei Xie, Lili Pan, “Research on iris image preprocessing algorithm”, IEEE Proceedings of the International Symposium on Communications and Information Technologies, pp.155-158.(2005)
[20] Manli Zhu, Aleix M. Martinez, “Subclass Discriminant Analysis”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, No.8, pp.1274-1286. (2006)
[21] Marcia Y. Jung, ”Biometric Market and Industry Overview”, International Biometric Group, World Customs Organization, December 8. (2005)
[22] N. Tun, “Recognising Iris Patterns for Person (or Individual) Identification”, Honours thesis, The University of Western Australia. (2002)
[23] Richard P Wildes, “Iris Recognition: An Emerging Biometric Technology”, Proceedings of the IEEE, Vol.85, No.9. (1997)
[24] Richard P Wildes, Jane C. Asmuth, Gilbert L Green, “A machine-vision system for iris recognition”, Machine Vision and Applications, Vol.9, No.1, pp.1-8.(1996)
[25] R. A. Fisher, ”The Statistical Utilization of Multiple Measurements” ,Annals of Eugenics, Vol.8, pp.376-386.(1938)
[26] R. Lotlikar and R. Kothari, “Fractional-step dimensionality reduction” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.22, pp.623-627. (2000)
[27] Rafael C. Gonzalez, Richard E. Woods, ”Digital Image Processing” Second Edition, ISBN：0130946508
[28] Richard P Wildes, Jane C Asmuth, Gilbert L Green, “A machine-vision system for iris recognition”, Machine Vision and Applications, Vol.9, No.1, pp.1-8.(1996)
[29] Sanchez-Avila C., Sanchez-Rei110 R.; de Martin-Roche D., “Iris recognition for biometric identification using dyadic wavelet transform zero-crossing”, Proceedings of the IEEE 35th International. Camahan Conference on Security Technology, pp. 272 -277. (2001)
[30] S. Nanavati, M. Thieme, R. Nanavati, “Biometrics:Identity Verification in a Networked World”, John Wiley&Sons. (2002)
[31] Vladimir VN, The Nature of Statistical Learning Theory. Springer, Berlin Heidelberg New York. (1995)
[32] W. W. Boles, ”A Security system based on human iris identification using wavelet transform”[J], Engineering Application of Artificial Intelligence, Vol.11. (1998)
[33] W. W. Boles, B. Boashash, “A Human Identification Technique Using Images of the Iris and Wavelet Transform”, IEEE Transactions on Signal Processing, Vol.46, No.4. (1998)
[34] Weiqi Yuan, Zhonghua Lin and Lu Xu, “A Novel and Fast Iris Location Algorithm Based on the Structure of Human Eyes”, Proceedings of the 6th World Congress on Intelligent Control and Automation,Vol.2, pp.10388-10392. (2006)
[35] X. Li, M. Xie, ”A novel algorithm of human iris recognition”, IEEE Proceedings of the International Symposium on Communications and Information Technologies, Vol.2, pp.1231-1234. (2005)
[36] 蔡博仁, ”多重特徵萃取與支持向量器為基礎的虹膜辨識技術”,國立暨南國際大學電機工程學系,碩士論文. (2005)
[37] 單維章, ”凌波初步”, 全華科技圖書. (2000)
[38] 黃智任, ”應用人眼特徵於身份辨認的系統介紹”影像與識別,第三卷第七期,92~94頁,民國八十五年.
[39] 靳濟芳, ”Visual C++ 小波變換與工程實踐”,人民郵電出版社.
[40] 池坤徽, ”以凌波轉換為基礎的虹膜辨識系統”, 國立暨南國際大學電機工程研究所論文,民國九十二年.
[41] 鐘國亮, “影像處理與電腦視覺”, 東華書局,民國九十一年.
[42] National Geographic Magazine, http://magma.nationalgeographic.com/ngm/afghangirl/index.html
[43] CASIA iris database http://nlpr-web.ia.ac.cn/english/irds/irisdatabase(c).htm
[44] Chang, C.-C. and C.-J. Lin(2001).LIBSVM:a library for support vector machines.Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm