網路世代來臨，使得人們越來越重視個人資料的安全防護，而傳統的身分識別的方法(如：鑰匙或密碼)卻不夠嚴實，不但被盜用的情況屢見不鮮，更有遺失或遺忘的可能。近年來，運用個體生物表徵為依據的生物辨識技術受到諸多的關注，由於個體生物表徵是與生俱來且獨一無二，不但不會遺失或遺忘，還具有優異的身分辨識度，使得傳統識別方式的缺點在生物辨識範疇內可獲得大幅的改善。儘管生物辨識技術具有許多的優點，但現存大多的生物辨識系統仍存有系統安全性和個人生理資訊隱私性受侵的疑慮。其原因在於生物表徵不像密碼或鑰匙可以刪除或更新，一旦被他人竊取，則將會永久失效；再者，被竊取的生物表徵也恐為他人用以推論個體的生理狀態資訊。有鑑於生物辨識技術將成為未來身分辨識方法的主流，故改善現階段生物辨識關於安全性和隱私性的缺點是刻不容緩的。目前一個可靠的解決方案便是可刪式生物辨識系統，故本研究選定可刪式生物辨識系統作為研究的標的，並提出以心電訊號為依據的可刪式生物辨識演算法。實驗結果顯示，本研究所提的可刪式生物識別演算法不但具有良好的個體辨識率，還具備了可刪式生物識別模板需具備的可更新性、不可逆和多樣化。

Biometric technologies have gained much interest recently. The identities of individuals are recognized by directly utilizing their physiological or behavioral characteristics. This removes the problems of conventional techniques such as forgetting passwords or losing keys. However, despite many advantages offered by these technologies, concerns about compromising individuals' privacy are accompanied for the reasons as follow. First, most of the biometric traits (e.g., fingerprints and faces) in use are extrinsic, which may be easily recorded without the owners’ consent. Moreover, the biometrics of an individual is permanently associated with him/her so that it is difficult to be revoked when stolen or compromised. Several attempts have been made to address these concerns, and "cancelable biometrics" is the one attracted the most attention. To reflect this trend, an ECG based cancelable biometric scheme is proposed in this study. Experiments with real ECGs showed that our proposed scheme achieved a recognition rate of 97.19%. Furthermore, the biometric templates generated by our proposed scheme fulfill all the requirements to be cancelable, including revocability, non-invertibility, and diversity.

摘要 i
Abstract ii
誌謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
第一章 緒論 1
1.1 研究緣起 1
1.2 心電訊號應用於生物辨識的優勢 3
1.3 論文架構 4
第二章 背景與文獻回顧 5
2.1 心電訊號簡介 5
2.2 生物辨識系統簡介 7
2.3現階段生物辨識系統的隱憂與解決之道 8
2.4 可刪式生物辨識演算法回顧 10
第三章 基於心電訊號的可刪式生物辨識演算法 11
3.1心電訊號導程數量 11
3.2 心電訊號預處理 11
3.3 生物識別模板的產生與分類 13
3.3.1 子空間斷定(subspace determination)的概念 13
3.3.2 Beat Bundle的訊號子空間與噪聲子空間 13
3.3.3 登錄訓練資料 14
3.3.4 驗證用戶身分 16
3.3.5 拒絕未登錄者的機制 23
第四章 實驗結果 25
4.1 心電訊號資料庫 25
4.2 系統評比 (Performance Evaluation) 26
4.3 可更新性 27
4.4辨識性能 29
4.4.1 維度對辨識率的影響 29
4.4.2 訓練/測試beat bundle之數量對辨識率的影響 30
4.4.3 取樣頻率對辨識率的影響 33
4.4.4 雜訊對辨識率的影響 34
4.5 不可逆性 36
4.5.1 暴力攻擊法 36
4.5.2 未登錄者的入侵 37
4.5.3 竊取模板攻擊 38
4.6 多樣性 39
第五章 結論 41
參考文獻 42

[1] A. K. Jain, A. Ross, and S. Prabhakar, "An introduction to biometric recognition," IEEE Trans. Circuits Syst. Video Technol, vol. 14, pp. 4-20, 2004.
[2] J. Unar, W. C. Seng, and A. Abbasi, "A review of biometric technology along with trends and prospects," Pattern Recog., vol. 47, pp. 2673-2688, 2014.
[3] N. K. Ratha, J. H. Connell, and R. M. Bolle, "Enhancing security and privacy in biometrics-based authentication systems," IBM Syst. J., vol. 40, pp. 614-634, 2001.
[4] A. K. Jain, K. Nandakumar, and A. Nagar, "Biometric template security," EURASIP J. on Advances in Signal Processing, vol. 2008, p. 113, 2008.
[5] S. Rane, Y. Wang, S. C. Draper, and P. Ishwar, "Secure biometrics: concepts, authentication architectures, and challenges," IEEE Signal Process. Mag., vol. 30, pp. 51-64, 2013.
[6] V. M. Patel, N. K. Ratha, and R. Chellappa, "Cancelable biometrics: A review," IEEE Signal Process. Mag., vol. 32, pp. 54-65, 2015.
[7] S. Prabhakar, S. Pankanti, and A. K. Jain, "Biometric recognition: Security and privacy concerns," IEEE Security Privacy, 2003.
[8] R. M. Bolle, J. H. Connell, and N. K. Ratha, "Biometric perils and patches," Pattern Recog., vol. 35, pp. 2727-2738, 2002.
[9] R. Belguechi, E. Cherrier, and C. Rosenberger, "How to Evaluate Transformation Based Cancelable Biometric Systems?," in NIST International Biometric Performance Testing Conference (IBPC), 2012.
[10] R. Belguechi, E. Cherrier, C. Rosenberger, and S. Ait-Aoudia, "An integrated framework combining Bio-Hashed minutiae template and PKCS15 compliant card for a better secure management of fingerprint cancelable templates," Comput. Secur., vol. 39, pp. 325-339, 2013.
[11] J. K. Pillai, V. M. Patel, R. Chellappa, and N. K. Ratha, "Sectored Random Projections for Cancelable Iris Biometrics," in Proc. IEEE Int. Conf. Acoust. Speech Signal Process, 2010, pp. 1838-1841.
[12] M. Savvides, B. V. Kumar, and P. K. Khosla, "Cancelable biometric filters for face recognition," in Proc. Int. Conf. Pattern Recognition, 2004, pp. 922-925.
[13] R Bousseljot, D Kreiseler, and A. Schnabel, "Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das internet," Biomedizinische Technik, vol. 40, p. s317, 1995.
[14] Y. Wang, F. Agrafioti, D. Hatzinakos, and K. N. Plataniotis, "Analysis of human electrocardiogram for biometric recognition," EURASIP J. on Advances in Signal Processing, vol. 2008, pp. 1-11, 2007.
[15] L. Biel, O. Pettersson, L. Philipson, and P. Wide, "ECG analysis: a new approach in human identification," IEEE Trans. Instrum. Mea., vol. 50, pp. 808-812, 2001.
[16] I. Odinaka, P.-H. Lai, A. D. Kaplan, J. A. O'Sullivan, E. J. Sirevaag, and J. W. Rohrbaugh, "ECG biometric recognition: A comparative analysis," IEEE Trans. Inf. Forensics Security, vol. 7, pp. 1812-1824, 2012.
[17] S. A. Israel, J. M. Irvine, A. Cheng, M. D. Wiederhold, and B. K. Wiederhold, "ECG to identify individuals," Pattern Recog., vol. 38, pp. 133-142, 2005.
[18] Y. N. Singh and S. K. Singh, "Identifying individuals using eigenbeat features of electrocardiogram," Journal of Engineering, vol. 2013, 2013.
[19] L. Sörnmo and P. Laguna, Bioelectrical signal processing in cardiac and neurological applications vol. 8: Academic Press, 2005.
[20] Online, " http://celestialmedicine.tumblr.com/post/106864492194."
[21] N. Dey, B. Nandi, M. Dey, D. Biswas, A. Das, and S. S. Chaudhuri, "Biohash code generation from electrocardiogram features," in 3rd IEEE International Advance Computing Conference, 2013, pp. 732-735.
[22] R. Hoekema, G. J. Uijen, and A. Van Oosterom, "Geometrical aspects of the interindividual variability of multilead ECG recordings," IEEE Trans. Biomed. Eng., vol. 48, pp. 551-559, 2001.
[23] C. Levkov, G. Mihov, R. Ivanov, I. Daskalov, I. Christov, and I. Dotsinsky, "Removal of power-line interference from the ECG: a review of the subtraction procedure," BioMedical Engineering OnLine, vol. 4, p. 1, 2005.
[24] P. De Chazal, C. Heneghan, E. Sheridan, R. Reilly, P. Nolan, and M. O'Malley, "Automated processing of the single-lead electrocardiogram for the detection of obstructive sleep apnoea," IEEE Trans. Biomed. Eng., vol. 50, pp. 686-696, 2003.
[25] J. Pan and W. J. Tompkins, "A real-time QRS detection algorithm," IEEE Trans. Biomed. Eng., pp. 230-236, 1985.
[26] R. Schmidt, "Multiple emitter location and signal parameter estimation," IEEE Trans. Antennas Propag., vol. 34, pp. 276-280, 1986.
[27] G. Strang, "Introduction to linear algebra," 2011.
[28] J. M. Irvine, S. A. Israel, W. T. Scruggs, and W. J. Worek, "eigenPulse: Robust human identification from cardiovascular function," Pattern Recog., vol. 41, pp. 3427-3435, 2008.
[29] P. McSharry and G. Clifford, "ECGSYN-A realistic ECG waveform generator," URL http://www. physionet. org/physiotools/ecgsyn, 2003.
[30] R. Moddemeijer, "On estimation of entropy and mutual information of continuous distributions," SigPr, vol. 16, pp. 233-248, 1989.