臺灣博碩士論文加值系統

近年來，人們對安全問題的重視，使得以生物辨識為基礎之身份辨識技術被人們所重視。在多種不同的生物辨識技術中，本論文將深入探討以人眼虹膜特徵為基礎的虹膜辨識技術，建立一套具有極佳辨識率的身份辨識系統。系統架構主要包含三個模組：影像前處理、特徵萃取與分類辨識模組。影像前處理模組利用影像處理演算法，自輸入人眼影像中取得需要之虹膜部份。再經由特徵萃取模組以本論文所提出之結合2D-PCA於2D-LDA方法，先找出類別內（within-class）較集中的訓練資料。接著以這些資料的平均作為類別代表資料，最後以2D-PCA找出能將這些代表資料在類別間（between-class）分散的降維矩陣。分類辨識模組，即可利用虹膜影像降維後得到的特徵向量，進行使用者註冊或辨識。
以葡萄牙內貝拉大學計算機科學系柔性演算暨影像分析學群，所提供的UBIRIS虹膜影像資料庫，對系統進行測試。UBIRIS.v1虹膜影像資料庫包含241類別，共1,205張影像，在影像前處理模組中，每類別以至少能成功切割出三張虹膜影像為標準，共232類別，1,133張影像。本系統提出之特徵萃取方式，以等錯誤率（equal error rate, EER）為標準，其辨識率為99.20%。本論文會針對實驗的數據結果進行分析比較，來驗證建構本系統時所提的相關推論，以供後續研究作為參考。

Recently, with an increasing emphasis on security, personal authentication based on biometrics has been receiving extensive attention. Among many different biometric technologies, this thesis examines iris recognition technique for personal identification and develops a good performance recognition system based on human iris features. The proposed system includes three modules: image preprocessing, feature extraction, and recognition modules. Image preprocessing module uses some image processing algorithms to localize the region of iris from the input image. The feature extraction module adopts 2D-LDA embedded with 2D-PCA method. Firstly, we find the more concentrated training samples, and calculate the sample mean in each class. Second, we employ the 2D-PCA to find projection matrix which can scatter the sample mean between classes. Eventually, the system applies these projected feature vectors for iris matching in recognition module.
It is implemented and tested on UBIRIS iris image database. The experimental results show that the system has an encouraging performance on the database. The recognition rate 99.20% can be achieved. Even under the circumstance of false acceptance rate（FAR）0%, the system still approaches the recognition rate above 97.80%. This thesis analyzes the experimental results to verify the related inferences of the proposed system and provides useful information for further research.

目錄
誌謝 i
論文摘要 ii
Abstract iii
目錄 iv
圖目錄 vii
表目錄 x
符號說明 xi
第一章 緒論 1
1.1 研究動機 1
1.2 虹膜辨識技術之發展與研究 2
1.3 研究目標與方向 6
1.4 論文大綱與組織 7
第二章 應用於人眼虹膜辨識之影像處理技術 8
2.1 彩色空間轉換 8
2.1.1 RGB彩色系統 8
2.1.2 HSI彩色系統 9
2.2 影像強化 10
2.2.1 基本灰階轉換 10
2.2.2 空間域濾波 12
2.3 形態學影像處理 14
2.4 圓形偵測 16
第三章 基本知識回顧與理論推導 19
3.1 主成份分析 19
3.1.1 主成份分析理論 19
3.1.2 二維主成份分析 22
3.2 線性識別分析 25
3.2.1 線性識別分析理論 25
3.2.2 二維線性識別 29
3.3 結合2D-PCA於2D-LDA理論推導 32
第四章 結合2D-PCA於2D-LDA虹膜辨識之研究 35
4.1 系統架構 35
4.2 人眼虹膜影像分析 36
4.3 影像前處理模組 38
4.3.1 虹膜定位 40
4.3.2 虹膜切割與座標轉換 46
4.3.3 影像強化 48
4.4 特徵萃取模組 49
4.4.1 2D-PCA特徵萃取方法 49
4.4.2 2D-LDA特徵萃取方法 51
4.4.3 結合2D-PCA於2D-LDA特徵萃取方法 51
4.5 分類辨識模組 53
第五章 虹膜辨識系統實作與實驗結果 54
5.1 實驗環境 54
5.2 系統效能評估 54
5.3 影像前處理模組 55
5.4 影像強化 57
5.5 2D-PCA 58
5.6 2D-LDA 59
5.7 結合2D-PCA於2D-LDA方法 61
5.8 分析與討論 62
第六章 結論與建議 65
6.1 結論 65
6.2 未來研究方向 66
參考文獻 67
作者簡介 69

[1]S. Prabhakar, S. Pankanti and A. K. Jain, “Biometric recognition: security and privacy concerns,” IEEE Trans. on Security ＆ Privacy, vol. 1, no. 2, pp. 33-42, 2003.
[2]“Harmonized Biometric Vocabulary,” ISO/IEC JTC1 SC37, standing document 2, version 8, 2007.
[3]S. Nanavati, M. Thieme, and R. Nanavati, Biometrics: Identity Verification in a Networked World, John Wiley & Sons, 2002.
[4]http://www.ibgweb.com/, Homepage of International Biometric Group.
[5]http://www.iridiantech.com/solutions.php, Homepage of Iridian Technologies.
[6]M. Negin, T. A. Chmielewski Jr., M. Salganicoff, U. M. von Seelen, P. L. Venetainer and G. G. Zhang, “An iris biometric system for public and personal use,” IEEE Trans. on Computer, vol. 33, no. 2, pp. 70-75, 2000.
[7]L. Flom and A. Safir, “Iris recognition system,” U.S. Patent, no. 4641349, 1987.
[8]J. Daugman, “High confidence visual recognition of persons by a test of statistical independence,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 15, No. 11, pp. 1148-1161, 1993.
[9]J. Daugman, “Biometric personal identification system based on iris analysis,” United States Patent, No. 5291560, 1994.
[10]J. Daugman, “How iris recognition works,” IEEE Trans. on Circuits and Systems for Video Technology, vol. 14, no. 1, pp. 21-30, 2004.
[11]W. Boles and B. Boashash, “A human identification technique using images of the iris and wavelet transform,” IEEE Trans. on Signal Processing, vol. 46, no. 4, pp. 1185-1188, 1998.
[12]C. Sanchez-Avila, R. Sanchez-Reillo and D. de Martin-Roche, “Iris-based biometric recognition using dyadic wavelet transform,” IEEE Aerospace Electron. System Magazine, vol. 17, no. 10, pp. 3-6, Oct. 2002.
[13]R. P. Wildes, “Automated, non-invasive iris recognition system and method,” United States Patent, no. 5572596, 1994.
[14]R. P. Wildes, “Iris recognition: an emerging biometric technology,” Proc. of the IEEE, vol. 85, no. 9, pp. 1348-1363, 1997.
[15]S. Lim et al., “Efficient iris recognition through improvement of feature vector and classifier,” ETRI Journal, vol. 23, no. 2, pp. 61-70, 2001.
[16]L. Ma, T. Tan, Y. Wang and D. Zhang, “A human identification technique using images of the iris and wavelet transform,” IEEE Trans. on Image Processing, vol. 13, no. 6, pp. 1185-1188, 2004.
[17]L. Ma, T. Tan, Y. Wang and D. Zhang, “Personal identification based on iris texture analysis,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 25, no. 12, pp. 1519-1533, 2003.
[18]D. M. Monro and D. Zhang, “An effective human iris code with low complexity,” Proc. of the IEEE Int. Conf. on Image Processing, vol. 3, pp. 277-280, 2005.
[19]D.M. Monro, S. Rakshit and D. Zhang, “DCT-based iris recognition,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 29, no. 4, pp. 586-595, 2007.
[20]林永淋，建構於圓規維與KL轉換之自動人眼虹膜辨識系統，國立暨南國際大學，碩士論文，民國91年。
[21]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，碩士論文，民國93年。
[22]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，碩士論文，民國94年。
[23]張順訓，虹膜辨識系統之影像擷取機構設計與虹膜影像品質估計之研究，國立暨南國際大學，碩士論文，民國94年。
[24]曹駿，利用序列虹膜影像進行辨識與抗偽造之研究，國立暨南國際大學，碩士論文，民國95年。
[25]Hugo Proenca and L. A. Alexandre. UBIRIS: A noisy iris image database, http://iris.di.ubi.pt/.
[26]R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2nd Edition, Prentice-Hall, New Jersey, 2002.
[27]J. R. Parker, Algorithms for Image Processing and Computer Vision, John Wiley & Sons, 1996.
[28]繆紹綱，數位影像處理－運用MATLAB，東華書局，台北市，民國94年。
[29]A. A. Rad, K. Faez and N. Qaragozlou, “Fast circle detection using gradient pair Vectors,” Proc. VIIth Digital Image Computing: Techniques and Applications, 2003.
[30]J. S. Jang, “Data clustering and pattern recognition,” (in Chinese) available at the links for on-line courses at the author's homepage at http://www.cs.nthu.edu.tw/~jang.
[31]R. A. Fisher, “The use of multiple measures in taxonomic problems,” Ann. Eugenics, vol. 7, pp. 179-188, 1936.
[32]J. Yang and J. Y. Yang, “From image vector to matrix: A straightforward image projection technique—IMPCA vs. PCA,” Pattern Recognition, vol. 35, no. 9, pp. 1997-1999, 2002.
[33]J. Yang, D. Zhang, A. F. Frangi and J. Y. Yang. “Two-dimensional PCA: a new approach to appearance-based face representation and recognition,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 26, no. 1, pp. 131-137, 2004.
[34]J. Yang and C. Liu, “Horizontal and vertical 2DPCA-based discriminant analysis for face verification on a large-scale database,” IEEE Trans. on Information Forensics and Security, vol. 2, no. 4, pp. 781-792, 2007.
[35]M. Li and B. Yuan, “2D-LDA: A novel statistical linear discriminant analysis for image matrix,” Proc. of the IEEE Int. Conf. on Signal Processing, vol. 2, no. 31, pp. 1419-1422, 2002.
[36]J. Yang, A. F. Frangi and D. Zhang, “Uncorrelated projection discriminant analysis and its application to face image feature extraction,” Int. J. of Pattern Recognition and Artificial Intelligence, vol. 17, no. 8, pp. 1325-1347, 2003.
[37] J. Yang and D. Zhang, “Two-dimensional discriminant transform for face recognition,” Pattern Recognition, vol. 38, no.7, pp. 1125-1129, 2005.
[38]J. Yang and C. Liu, “On image matrix based feature extraction algorithms,” IEEE Trans. on Systems, Man and Cybernetics-PART B: Cybernetics, vol. 36, no. 1, pp. 194-197, 2006.