在本論文中,我們提出了一套「虹膜辨識系統」。虹膜是指瞳孔周圍的肌肉組織，人的虹膜上有很多微小的凹凸起伏和條狀組織，具有獨特結構。基於這種生物特徵，我們提出一種有別於過去較常出現的四種虹膜識別的技術，稱為以最佳路徑匹配搜尋為基礎的虹膜是別方法。過程是以匹配搜尋演算法去擷取具有鑑別性的特徵向量，並利用最佳路徑搜尋法改良，得到最佳特徵擷取，最後將最佳路徑與特徵圖儲存到電腦資料庫。匹配收尋為一種以最少特徵向量表示特徵圖為原則的演算法，對於每次匹配皆選取最相似特徵圖的特徵向量。由於匹配順序會對整體匹配有所影響，利用最佳路徑收尋法來尋找最佳的匹配路徑，以取得最佳效果。進行身份識別時，只需取得檢測者的虹膜特徵資料，依照該身分最佳路徑執行匹配，並與該身分特徵圖作比對，即可得知是否為非法假冒者。
實驗的進行主要在三個方面作比較。首先，使用verification模式計算正確識別率，確認此系統識別能力；於identification模式中，計算FMR curve與FNMR curve，利用此兩線路畫出ROC curve以描述系統整體的強健度；最後紀錄系統識別所執行時間，驗證系統執行效率。結果發現此虹膜辨識具有相當高的鑑別率，擁有高達98.75%以上的識別率，ROC curve描述出系統較改良前強健，且識別動作所發費的時間只需不到1秒。

In my thesis, we propose a new method named Dynamic Programming Based Matching Pursuit algorithm for iris-based personal identification. The method modifies the matching pursuit algorithm so that it selects the most representative path to do iris recognition. Our system consists of three parts: identification, verification and performance evaluation. The experimental results demonstrate the efficacy of the proposed method by showing that it attains a better ROC curve and faster speed than the conventional matching pursuit based iris recognition system.

[1] J. Daugman, ”High confidence visual recognition of persons by a test of statistical independence” IEEE Trans. Pattern Anal. Mach. Intell. , vol.15, no.11, pp.1148–1161, Nov.1993.
[2] Inventors: Kodno, Kenji (Hirakata, JP), Uomori, Kenya (Hirakata, JP), “Frequency and resolution analyzed biometric authentication method and device”, Patent - United States Patent 7,099,495
[3] Francois Bergeaud and Stephane Mallat,“ Matching pursuit of images ”.Matching pursuit of images ,pp. 1-16
[4] S. Malat and Z. Zhang. “Matching Pursuit with time-frequency dictionaries”, IEEE Trans. On Signal Processing, Dec. 1933.
[5] L.K. Jones, “On a conjecture of Huber concerning the convergence of projection pursuit regression”, The Annals of Statistics, vol. 15, No.2,pp. 880-882, 1987.
[6] Richard P. Wildes, Jane C. Asmuth, Gilbert L.Green, Steven C. Hsu, Raymond J. Kolczynski, James R. Matey, Sterling E.McBride,“A Machine-Vision System for Iris Recognition”, Machine Vision and Application (1996) 9:1-8.
[7] R. Neff and A. Zakhor, “Very Low Bit-rate Video Coding Based on Matching Pursuits”, IEEE Trans. On Circuits and System for Video Technology, FEB. 1997
[8] Sean R Eddy, “What is dynamic programming”, Nature Biotechnology Volume22 Number 7 July 2004
[9] Y. Zhu, T. Tan, and Y. Wang, “Biometric personal identification based on iris patterns,” in Proc. 15th Int. Conf. Pattern Recognition, vol. II, 2000, pp. 805–808.
[10] L. Ma, Y. Wang, and T. Tan, “Iris recognition based on multi-channel Gabor filtering,” in Proc. 5th Asian Conf. Computer Vision, vol. I, 2002, pp. 279–283.
[11] L. Ma, Y. Wang, and T. Tan, “Iris recognition using circular symmetric filters,” in Proc. 16th Int. Conf. Pattern Recognition, vol. II, 2002, pp. 414–417.
[12] L. Ma, T. Tan, Y.Wang, and D. Zhang, “Personal identification based on iris texture analysis,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 12, pp. 1519–1533, Dec. 2003.
[13] Li Ma, Tieniu Tan, Yunhong Wang, and Dexin Zhang, “Efficient Iris Recognition by Characterizing Key Local Variations”, IEEE TRANS. Image Processing, VOL. 13, NO. 6,JUNE 2004
[14] Zhenan Sun, Yunhong Wang, Tieniu Tan, Jiali Cui; “Improving iris recognition accuracy via cascaded classifiers”, IEEE Transactions on Volume 35, Issue 3, Aug. 2005 Page(s):435 – 441
[15] Weiqi Yuan, Zhonghua Lin, Lu Xu; “A Novel and Fast Iris Location Algorithm Based on the Structure of Human Eyes”, The Sixth World Congress on Volume 2, 21-23 June 2006 Page(s):10388 - 10392”
[16] Jian-Liang Lin, Wen-Liang Hwang, Soo-Chang Pei; “Video compression based on orthonormal matching pursuits”, Circuits and Systems, 2006. ISCAS 2006. Proceedings. 2006 IEEE International Symposium on 21-24 May 2006 Page(s):4 pp.
[17] CASIA Iris Image Database [Online] Available: http://www.sinobiometrics.com/casiairis.htm