臺灣博碩士論文加值系統

在這許多的生物辨識的研究及應用中，以人類眼睛的虹膜為生物辨識特徵的方法是最安全也是最可靠的，本研究也對於虹膜特徵的擷取與量化的方法，提出不同的方式來建立由特徵影像量化虹膜特徵值，此一方法也可應用在中醫在眼診領域上的研究，提供一個虹膜特徵量化之數據以供眼診判斷之參考。

在影像擷取的階段中，虹膜影像的擷取可說是重要的關鍵性步驟。虹膜影像的擷取受到了擷取裝置解析度、打光方式、打光角度、打光亮度、焦距、及被取樣者的眼睛狀態等等因素所影響。眼瞼覆蓋虹膜的區域也是有待克服的部分，過大的覆蓋區域將會使虹膜特徵資訊大大的減少，直接影響特徵建立的有效性。這些變數都是會影響後續的特徵處理所形成的特徵型態與分佈。本文所提之方法為擷取虹膜特徵區域之邊緣座標，而特徵區域的位置及分佈就是特徵座標點的依據。
本文中所提出之虹膜特徵的擷取與量化創新方法，包括環形邊緣檢測、瞳孔位置搜尋、虹膜位置搜尋、影像二值化、特徵處理、特徵標示與特徵座標點建立、特徵序列比對、比較係數法、虹膜驗證比對等步驟，最後並針對特徵序列數量符合之特徵資料進行第二階段的特徵值比較係數之計算與分析。在實驗中，不同的特徵影像經由特徵序列比對及比較係數法的計算之後，均可以表現出各獨立虹膜之特性及其特有之特徵值。

虹膜影像的擷取過程對於系統之效能有極大的影響，為求系統之準確性與強健性，本方法在前端建立一個穩定的影像擷取系統，對於後端之處理有很大的幫助。穩定的影像擷取方法與環境將可以使後端的影像處理更簡單更有效率，也更可以用更簡單的方法來達到虹膜辨識的功能及要求。

In the biometrics identification applications, the Iris recognition is the most reliable and accurate method. In this paper, we propose a new method to achieve acquisition and quantification of human iris patterns.
This method for iris feature extraction and quantification comprises of steps for initial starting up, the acquisition of iris image data, the identification of pupil location, spoke edge detection, iris feature extraction, iris patterns quantification, verification with features in database. Within these steps, step for personal identification detects on: a group of feature parameters of color in one zone, coefficient of comparison in vertical and horizontal scan line.
The experimental results verified that this image system provides an economical and effective method for iris feature extraction and quantification. We believe the objective of this new method will provide a highly effective and efficient method and apparatus for conducting security access control and health consultation and management.

致謝 i
中文摘要 iii
Abstract iv
目 錄 ivv
圖 目 錄 vi
表 目 錄 iviii
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的及其重要性 2
1.3 文獻回顧 2
1.3.1 眼睛的構造 2
1.3.2 虹膜 Iris 6
1.3.3 彩色系統 8
1.3.4 生物辨識種類與方法 9
1.3.5 文獻回顧 12
第二章 研究理論與方法 2020
2.1 研究理論 2020
2.1.1 彩色系統 23
2.1.2 空間濾波 Spatial filters 22
2.1.3 梯度濾波器Gradient filters 23
2.1.4 拉普拉斯濾波器 Laplacian filters 24
2.1.5 邊緣檢測 Edge detection 25
2.1.6 環形邊緣檢測(Spoke Edge detection) 26
2.1.7 Clamp Function 27
2.2 研究方法 2828
2.2.1 打光安全考量 33
2.2.2成像原理 30
2.2.3 眼球中心位置搜尋 32
2.2.4 瞳孔位置搜尋 34
2.2.5虹膜位置搜尋 37
2.2.6 影像二值化 39
2.2.7 特徵處理 47
2.2.8 特徵標示與特徵座標點建立 42
2.2.9 特徵序列比對 44
2.2.10 影像XOR運算 45
2.2.11 比較係數法 46
第三章 結果與討論 48
3.1 特徵比對 48
3.1.1 虹膜特徵值 48
3.1.2 虹膜驗證比對 (Iris Verification) 53
3.1.3虹膜驗證結果 (Iris Verification Results) 61
3.2 虹膜比對 (Iris identification) 63
3.2.1 虹膜比對比較係數 63
3.2.2虹膜比對結果 68
3.3 討論 69
第四章 檢討與未來展望 71
參考文獻 73

[1] John Daugman, “How Iris Recognition Works”, IEEE Transactions on and system
for video technology, vol. 14, NO.1 , January 2001, pp. 1-10.
[2] Gerald O. Williams, “Iris Recognition Technology”, Iridian Technologies, Inc.
[3] John Daugman, “Biometrics Decision Landscapes”, University of Cambridge, The computer laboratory, 2001, pp. 6-10.
[4] John Daugman, “The importance of being random: statistical principles of iris recognition”, The Computer Laboratory, University of Cambridge, Cambridge CB3 0FD, UK, Received 21 December 2001, pp. 5-12.
[5] National Instrument Vision Builder & IMAQ Concept Manual 2004, pp. 73-196.
[6] Michael Negin, Thomas A.,”An Iris Biometric System for Public and Personal Use”, IEEE Computer Science, 2000, pp. 4-12.
[7] Yong Zhu, Tieniu Tan and Yunhong Wang, “Biometrics Personal Identification
Based on Iris Patterns”, National Laboratory of Pattern Recognition (NLPR),
Institute of Automation, Chinese Academy of Sciences 1999, pp. 1-4.
[8] John Daugman, “High Confidence Recognition of persons by Their Iris Patterns”,
University of Cambridge, The Computer Laboratory, Cambridge CB2 3QG, U.K.
2001, pp. 9-17.
[9] Christel-loïc TISSE, Lionel MARTIN, Lionel TORRES , Michel ROBERT,
“Personal identification technique use human iris recognition”, Advanced
System Technology STMicroelectronics – ZI Rousset – 13106 Rousset Cedex,
France, 1999, pp. 2-5.
[10] RICHARD P. WILDES, ”Iris Recognition: An Emerging Biometric Technology”
proceeding of the IEEE, vol. 85, NO. 9, September 1997, pp. 4-6.
[11] JOAQUIM DEMIRA JR., JOCELIMAYER, “Image Feature Extraction for
Application of Biometric Identification of Iris-A Morphological Approach”,
Proceedings of the XVI Brazilian Symposium on Computer Graphics and Image
Processing (SIBGRAPI’03), IEEE 2003, pp. 5-12.
[12] Jain Jang, Kwiju Kim and Yillbyung Lee,”Efficient Algorithm of Eye Image
Check Robust Iris Recognition System”, Division of Computer and Information
Engineering, and of BERC, Yonsei University 2001, pp. 10-21.
[13] Penny Khaw, “Iris Recognition Technology for Improved Authentication”, SANS Institute 2002, pp. 3-12.
[14] John Daugman, “Iris recognition”, American Scientist, Volume 89, July 2001, pp. 1-7.
[15] Aaron Lefohn, Brian Budge, and Peter Shirley,”An Ocularist’s Approach to
Human Iris Synthesis”, IEEE Computer Society, 2003, pp. 2-10.
[16] W. W. Boles ,”A Security System Based on Human Iris Identification Using
Wavelet Transform”, IEEE, 1997, pp. 3-9.
[16] http://en.wikipedia.org/wiki/Statistical_independence
[18] http://home.t-online.de/home/manfred.bromba/biofaqe.htm
[19] http://www.webvision.med.utah.edu/anatomy.html
[20] Richard Caruso and Erik Reinhard, “An Ocularist’s Approach to Human Iris
Synthesis”, Aaron Lefohn, Brian Budge, and Peter Shirley University of Utah, IEEE Computer Society, November/December 2003, pp. 1-7.
[21] Shinyoung Lim , Kwanyong Lee, Okhwan Byeon, and Taiyun Kim, “Efficient Iris Recognition through Improvement of Feature Vector and Classifier”, ETRI Journal, Volume 23, Number 2, June 2001, pp. 1-8.