BioEncoding: A Reliable Token less Cancelable Biometrics Scheme for Protecting Iris Codes

被引:26
作者
Ouda, Osama [1 ]
Tsumura, Norimichi [1 ]
Nakaguchi, Toshiya [1 ]
机构
[1] Chiba Univ, Grad Sch Adv Integrat Sci, Chiba 2638522, Japan
来源
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | 2010年 / E93D卷 / 07期
关键词
biometric authentication; biometric encryption; cancelable biometrics; BioEncoding; BioHashing; lrisCode; RECOGNITION; SECURITY; KEYS;
D O I
10.1587/transinf.E93.D.1878
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Despite their usability advantages over traditional authentication systems, biometrics-based authentication systems suffer from inherent privacy violation and non-revocability issues. In order to address these issues, the concept of cancelable biometrics was introduced as a means of generating multiple, revocable, and noninvertible identities from true biometric templates. Apart from BioHashing, which is a two-factor cancelable biometrics technique based on mixing a set of tokenized user-specific random numbers with biometric features, cancelable biometrics techniques usually cannot preserve the recognition accuracy achieved using the unprotected biometric systems. However, as the employed token can be lost, shared, or stolen, BioHashing suffers from the same issues associated with token-based authentication systems. In this paper, a reliable tokenless cancelable biometrics scheme, referred to as BioEncoding, for protecting Iris Codes is presented. Unlike BioHashing, BioEncoding can be used as a one-factor authentication scheme that relies only on sole Iris Codes. A unique noninvertible compact bit-string, referred to as BioCode, is randomly derived from a true Iris Code. Rather than the true Iris Code, the derived BioCode can be used efficiently to verify the user identity without degrading the recognition accuracy obtained using original Iris Codes. Additionally, BioEncoding satisfies all the requirements of the cancelable biometrics construct. The performance of BioEncoding is compared with the performance of BioHashing in the stolen-token scenario and the experimental results show the superiority of the proposed method over BioHashing-based techniques.
引用
收藏
页码:1878 / 1888
页数:11
相关论文
共 32 条
[1]  
Ang R, 2005, LECT NOTES COMPUT SC, V3574, P242
[2]  
[Anonymous], CASIA Iris Image Database
[3]  
[Anonymous], 2004, PATTERN RECOGN, DOI DOI 10.1016/j.patcog.2004.04.011
[4]  
[Anonymous], 2009, HDB FINGERPRINT RECO
[5]   Biometric perils and patches [J].
Bolle, RM ;
Connell, JH ;
Ratha, NK .
PATTERN RECOGNITION, 2002, 35 (12) :2727-2738
[6]   Image understanding for iris biometrics: A survey [J].
Bowyer, Kevin W. ;
Hollingsworth, Karen ;
Flynn, Patrick J. .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2008, 110 (02) :281-307
[7]  
Cavoukian A., 2007, Biometric encryption: a positive-sum technol- ogy that achieves strong authentication, security and privacy
[8]  
Chang EC, 2007, LECT NOTES COMPUT SC, V4642, P750
[9]  
Cheung KH, 2005, LECT NOTES ARTIF INT, V3683, P1168
[10]   High security Iris verification system based on random secret integration [J].
Chin, CS ;
Jin, ATB ;
Ling, DNC .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2006, 102 (02) :169-177