生物辨識近年來已被廣泛的應用於各種個人身份與辨識的用途上;且愈形重要。以目前盛行的PIN(Personal Identification Number)辨識來說,光是銀行業每年在自動提款機因為錯誤接受(false acceptance)的損失就高達300億元[21]。自美國紐約在2001年發生911事件後,個人身份辨識的正確性變得更為重要,而生物辨識所具備的唯一性相形受到了更大的重視。而虹膜辨識正是生物辨識的一種。
目前虹膜辨識相關的研究已經行之多年,但大部所採用的方法都極為複雜;相對而言其所耗費的系統資源也高。既然虹膜的特徵僅是由各種圖案複雜程度不同的區塊所組成,本論文使用中國科學院自動化研究所提供的CASIA人眼虹膜影像資料庫[20],試圖應用影像處理的技巧,使用虹膜特徵最明顯的且最不易受到干擾的4個區域,組合成一個特徵區塊;在特徵強化的情況下,僅使用區塊切割後的平均值(Mean)與變異數(Variance)即可達到圖片配對成功率81.25%,且人員辨識成功率達96.3%。在比照使用相同資料庫之論文[23],排除不適用之圖片後,在圖片利用率87.04%的狀況下,得到的等錯誤率為3.03%。
最後我們將此辨識方式應用於實作,使用CCD進行實際上人眼的拍攝。相較於使用事先擷取並放大的照片做為實體測試[29],我們採用了CCD直接對人眼擷取的方式。在樣本數為10的情況下,可100%正確辨識。

Today, biometrics has been applied to personal recognition popularly, & more important. For instance, the PIN (Personal Identification Number), which was used to ATM (Automated teller machine), caused the loss of bank almost 30 thousands of millions due to false acceptance [21]. In 1991, Sep 11, terrorists attacked New York & caused inestimable loss of lives & cost; for avoid this matter, United States do their best to have the most correct identification in every where & the unique of biometric is just what we want.
Iris recognition, one kind of biometrics, has been adopted so many years, but the methods of recognition almost are very complex & consume much resource. Since the characteristics of IRIS are made up by different patterns, in this thesis, we try to apply some methods of image processing to the data base, which is provided by CASIA [20], & hope to do well recognition. We only catch 4 blocks of IRIS in the image, which are pure & distinct, make up them to be a new block called as characteristic block. After emphasized the image of characteristic block, the matching rate of pictures could be 81.25%, & 96.3% in person matching if we count the mean & variance of characteristic blocks. Compare to the thesis which use the same CASIA database [23], follow authors suggestion, we eliminate some images that are not suitable for recognition. After that, the useable rate of images is 87.04%, & we got the 3.03% of EER.
Finally, we try to implement this system & catch images via CCD directly replace pre-caught images [29], the matching rate is 100% when we test total 10 persons.

[1] A. C. Bovik, M. Clark, & W. S. Geisler, “Multichannel texture analysis using localize spatial filters,” IEEE Trans. Pattern Anal. Machine intell., vol. 12 pp.55~73, 1990.
[2] T. Caelli, “On discriminating visual textures & images,” Perception & Psychophysics, vol.31, pp. 149~159, 1982.
[3] John G. Daugman, “High confidence visual recognition of persons by a test of statical independence,” IEEE Trans.Patt.Anal. and Machine Intell.,vol.15,no.11,pp.1148~1161,1933.
[4] John G. Daugman, “Two dimensional spectral analysis of cortical receptive field profiles,” Vision Res. vol. 20, pp.847~856, 1980.
[5] John G. Daugman, “Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters,” J. Opt. Soc. Amer. A, vol. 2, pp. 1160~1169,1985.
[6] John G. Daugman, “High confidence recognition of persons by iris patterns,” IEEE 35th International Carnahan conference on Security Technology,254~263,2001.
[7] R. S. Feris, T. E. Campos, and R. M. Cesar, “Detection and tracking of facial features in video sequences,” in Mexican International Conference on Artificial Intelligence, pp. 129-137, 2000.
[8] L. Flom and A. Safir, “Iris recognition system,” U.S.Patent, no.4641349,1987.
[9] R. C. Gonazlez and R. E. woods, Digital image processing, 2nd. Addison-wesley, 1992.
[10] R. L. Hsu, M. A. Mottaleb, and A. K. Jain, “Face detection in color images,” IEEE Trans. Pattern Analysis and Machine Intell., vol. 24, pp. 696-706, 2002.
[11] A. K. Jain, “Fundamentals of digital image processing,” Englewood Cliffs, NJ: Prentice-Hall, 1989.
[12] A. K. Jain and F. Farrokhnia, “Unsupervised texture segmentation using Gabor filters,” Pattern Recognit., vol. 24, pp.1167~1186, 1991.
[13] T. K. Kim, J. K. Paik, and B. S. Kang, “ Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering,” IEEE Trans. on Consumer Electronics, vol. 44, no. 1, pp. 82-86, Feb. 1998.
[14] Y. T. Kim, “Contrast enhancement using brightness preserving bi-his togram equalization,” IEEE Trans. Consumer Electron., vol. 43 , no. 1, pp. 1-8, Feb. 1997.
[15] L. Ma, et al., “Personal identification base on iris texture analysis,” IEEE Trans. on Patt. Anal. & Machine intell., vol. 25, no. 12, pp. 1519~1533, 2003.
[16] Hanho Sung, Jaekyung Lim, Ji-hyun Park, Yillbyung Lee, “Iris Recognition Using Collarette Boundary Localization,” ICPR (4) ,857~860,2004.
[17] R. P. Wildes, “Automated, non-invasive iris recognition system and method,” United States Patent, no.5572596, 1994.
[18] R. P. Wildes, “Iris recognition: an emerging biometric technology,” Proc. of the IEEE, vol.85, no.9, pp. 1348~1363, 1997.
[19] Y. Zhu, T. Tan, and Y. Wang, “Biometric personal identification base on iris patterns,” Proc. Int’l Conf. Pattern Recognition, vol. 2. pp.805~808, 2000.
[20] Institute of Automation, Chinese Academy of Sciences, CASIA Iris Image Database, http://WWW.sinobiometrics.com/
[21] http://www.hightechcareers.com/doc198/biometrics198.html
[22] http://www.dls.ym.edu.tw/neuroscience/bigeye_c.html
[23] 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。
[24] 吳健康, 數位影像分析,儒林圖書,民國八十一年。
[25] 莊英杰, “追瞳系統之研發於身障者之人機介面應用,”國立中央大學資訊工程研究所碩士論文, 民國九十三年。
[26] 陳朝欽, 王聖文, 陳育誼, 生物辨識與認證, 國立清華大學資訊工程學系會刊, 民國九十二年。
[27] 張智星, 資料分群與樣式辨認 (Date Clustering and pattern recognition), http://neural.cs.nthu.edu.tw/jang/books/dcpr
[28] 楊元韶, “以類免疫系統為基礎之線上學習類神經模糊系統及其應用,”國立中央大學資訊工程研究所碩士論文, 民國九十三年。
[29] 楊勁柏, ” 以Java語言實作自動虹膜辨識系統,” 國立暨南國際大學電機工程研究所論文, 民國九十二年。
[30] 鐘國亮, 影像處理與電腦視覺,東華書局,民國九十一年。