在本論文中,我們提出了二個和眼睛相關的研究，分別是基於電腦視覺下的「眼控人機介面」以及「虹膜辨識系統」。眼控人機介面的主軸為利用使用者睜閉眼睛的時間週期做為信號輸出來下達命令。其中包含了三個主要的程序：眼睛追蹤、判定睜閉眼與紀錄週期、命令信號處理。我們利用樣版比對法追蹤眼睛;由Support Vector Machine判斷開閉眼並紀錄其週期，最後再利用動態規劃法針對使用者所發出的信號和我們的命令信號做一個距離的比對，將信號分類至正確的命令。本系統主要是應用於醫療方面，造福一些肢體行動不便的患者，使其可以輕易的利用眼睛來和外界做一個溝通。在實驗中我們總共辨識九種命令信號來測試我們的系統，而辨識率都在90%以上。
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，我們提出虹膜識別的技術。過程是以匹配搜尋演算法去擷取具有鑑別性的特徵向量，儲存到電腦資料庫，需進行身份識別時，只需比對待檢測者的虹膜特徵資料，即可辨識個人身份。在運算的過程當中，為提升運算速度，我們使用快速傅立葉轉換(FFT)和Haar filter。實驗是以二種比對的模式(verification，identification)。結果我們發現虹膜辨識具有相當高的鑑別率，在這兩種模式的比對下均有高達98%以上的識別率。

This thesis consists of two parts: eye wink control interface and iris recognition. In the first part, we developed a user interface based on eye wink control scheme. We apply the support vector machine and template matching algorithm to detect and track eye winks. After that, the dynamic programming is used to estimate the input commands. Thus, users can control the computer-based device according to their varying duration of eye winks.
In the second part, we propose an iris recognition method by using the matching pursuit algorithm to extract the most significant features of iris. The feature extraction includes two parts: iris location and feature extraction. We apply the matching pursuit algorithm to extract the most significant features, and eliminate the unnecessary information in order to reduce the dimension of iris signal. The identification of irises is based on the similarity between the corresponding feature vectors. The experimental results show the performance and efficiency of our proposed framework.

[1] Paul Smith, Mubarak Shah, and N. da Vitoria Lobo, “Monitoring Head/Eye Motion for Driver Alertness with One Camera”, The Fifteenth IEEE International Conference on Pattern Recognition. Nov.2000.
[2] T. D’Orazio, M.Leo,P.Spagnolo, C. Guaragnella,“Aneural system for eye detection in a driver vigilance application”, IEEE Trans. Conference, October 2004.
[3] V. Vapnik, The Nature of Statistical Learning Theory. New York: Springer, 1995.
[4] N Otsu, “A threshold selection method from gray-level histograms” IEEE Transactions on Systems, Man, and Cybernetics. 1979
[5]Sean R Eddy, “What is dynamic programming”, Nature Biotechnology Volume22 Number 7 July 2004
[6] P. W. Hallinan,“Recognizing human eyes”, Geometric Methods Comput. Vision, vol. 1570, pp. 214-226, 1991.
[7] W. W. Boles and B. Boashash,“A Human Identification Technique Using Image of the Iris and Wavelet Transform”, IEEE Trans. Signal Processing, vol. 46, ppl1185-1188, Apr. 1988.
[8] S. G. Mallat, “Zero-crossings of a Wavelet Transform”, IEEE Trans. Inform. Theory, vol. 37, no. 14, pp. 1019-2033, 1991.
[9] J. Daugman, “High confidence visual recognition of persons by a test of statistical independence”, IEEE Trans. Pattern Analy. Machine Intell., vol. 15, pp. 1148–1161, Nov. 1993.
[10] “Statistical richness of visual phase information: update on recognizing persons by iris patterns,” Int. J. Comput. Vis., vol. 45, no. 1, pp. 25–38, 2001.
[11] “Demodulation by complex-valued wavelets for stochastic pattern recognition,” Int. J.Wavelets, Multi-Res. and Info. Processing, vol. 1, no. 1, pp. 1–17, 2003
[12]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.
[13] 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.
[14] 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.
[15] 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.
[16]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
[17] Francois Bergeaud and Stephane Mallat,“ Matching pursuit of images ”.Matching pursuit of images ,pp. 1-16
[18] J. Daugman, “High confidence visual recognition of persons by a test of statistical independence”, IEEE Trans. Pattern Analyse. Machine Intell., vol. 15, pp. 1148–1161, Nov. 1993.
[19] S. Malat and Z. Zhang.“Matching Pursuit with time-frequency dictionaries”, IEEE Trans. On Signal Processing, Dec. 1933.
[20] 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.
[21] 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
[22] Shaw, R., Crisman, E., Loomsi, A., & Laszewski, Z. (1990). “The Eye Wink Control Interface: Using the Computer to Provide the Severely Disabled with Increased Flexibility and Comfort”, Third Annual IEEE Symposium on Computer-Based Medical Systems, pp.105-111.