Design of a High Secure Authentication System Based on Fuzzy Fusion of Iris and Face and Incorporating 2D Baker and Henon Maps
Keywords:Crypto-biometrics, Iris Recognition, Face Recognition, Chaotic Encryption, and Fuzzy Logic Fusion
The emergent concerns of identity theft problems and terrorism make the design of applicable accurate verification systems more crucial. No single biometric identifier could perfectly own all desired security properties. Moreover, the transmitted or stored biometric templates raise the opportunity of compromising user's privacy and identity breaching. This paper offers new scheme based on score level fuzzy fusion at decision level fusion to effectively combine face and iris identifiers. The proposed system allows an efficient identification procedure and introduces a new template locking approach based on chaos cryptography to protect the biometric data. In this study, CASIA and Faces94 databases are used to examine and appraise the robustness of the proposed schemes. The proposed template protection scheme offers new different uncorrelated secure forms of the base original templates in imperative and much speedy ciphering methodology. Furthermore, it could be rescinded at different points of probable attacks from sensed level to the final code and the matcher. It presents remarkably good key sensitivity and more robustness against different malicious attacks compared to classical encryption techniques. Furthermore, being noninvasive to the recognition process, simulation results on authentication rates introduces FAR and FRR of 0.0345%, and 0.001% respectively which illustrated a significant enhancement of the proposed fuzzy fusion over each unimodal system and existing multimodal fusion methods.
D. T. Meva, â€œComparative Study of Different Fusion Techniques in Multimodal Biometric Authentication,â€ vol. 66, no. 19, pp. 16â€“19, 2013.
A. Ross and R. Govindarajan, â€œFeature level fusion using hand and face biometrics,â€ Proc. SPIE - Int. Soc. Opt. Eng., vol. 5779, no. March, pp. 196â€“204, 2005.
J. BigÃ¼n, G. Chollet, and G. Borgefors, Eds., Audio- and Video-based Biometric Person Authentication, vol. 1206. Berlin, Heidelberg: Springer Berlin Heidelberg, 1997.
H. Benaliouche and M. Touahria, â€œComparative study of multimodal biometric recognition by fusion of iris and fingerprint,â€ Sci. World J., vol. 2014, 2014.
J. I. A. N. Q. Gao, L. I. Y. A. Fan, L. I. Li, and L. I. Z. Xu, â€œA PRACTICAL APPLICATION OF KERNEL â€“ BASED FUZZY DISCRIMINANT ANALYSIS,â€ vol. 23, no. 4, pp. 887â€“903, 2013.
O. Sharifi and M. Eskandari, â€œOptimal Face-Iris Multimodal Fusion Scheme,â€ Symmetry (Basel)., vol. 8, no. 6, p. 48, 2016.
H. Y. liu Yang, yue Xue Dong, Liu Ying Fei, â€œIris Recognition System Based on Chaos Encryption,â€ 2010 Int. Conf. Comput. Des. Appliations (ICCDA 2010), vol. 1, no. Iccda, pp. 537â€“539, 2010.
A. K. Jain, K. Nandakumar, and A. Nagar, â€œBiometric Template Security,â€ EURASIP J. Adv. Signal Process, vol. 2008, no. January, p. 113:1--113:17, 2008.
F. Hao, R. Anderson, and J. Daugman, â€œCombining crypto with biometrics effectively,â€ IEEE Trans. Comput., vol. 55, no. 9, pp. 1081â€“1088, 2006.
M. A. M. Abdullah, S. Dlay, W. Woo, and J. Chambers, â€œA Framework for Iris Biometrics Protection: A Marriage between Watermarking and Visual Cryptography,â€ IEEE Access, vol. 3536, no. c, pp. 1â€“1, 2016.
C. A. of S. Institute of Automation, â€œCASIA iris image database,â€ 2004. [Online]. Available: http://biometrics.idealtest.org/dbDetailForUser.do?id=1. [Accessed: 25-Jan-2017].
M. M. Eid, M. A. Mohamed, and M. A. Abou-El-Soud, â€œDevelopment of Iris Security System Using Adaptive Quality-Based Template Fusion,â€ in Intelligent Data Analysis and Applications: Proceedings of the Second Euro-China Conference on Intelligent Data Analysis and Applications, ECC 2015, A. Abraham, X. H. Jiang, V. SnÃ¡Å¡el, and J.-S. Pan, Eds. Cham: Springer International Publishing, 2015, pp. 265â€“278.
â€œFace Recognition Data.â€ [Online]. Available: http://cswww.essex.ac.uk/mv/allfaces/faces94.html. [Accessed: 03-May-2017].
M. A. Mohamed, M. E. Abou-Elsoud, and M. M. Eid, â€œAutomated face recogntion system: Multi-input databases,â€ in The 2011 International Conference on Computer Engineering & Systems, 2011, pp. 273â€“280.
S. Viriri and J. R. Tapamo, â€œIntegrating iris and signature traits for personal authentication using user-specificweighting,â€ Sensors, vol. 12, no. 4, pp. 4324â€“4338, 2012.
H. G. Schuster, Deterministic Chaos. 2005.
G. Ye and X. Huang, â€œA secure image encryption algorithm based on chaotic maps and SHA-3,â€ Secur. Commun. Networks, vol. 9, no. 13, p. n/a-n/a, 2016.
H. B. Kekre, V. A. Bharadi, V. I. Singh, V. Kaul, and B. Nemade, â€œHybrid Multimodal Biometric Recognition using Kekre â€™ s Wavelets , 1D Transforms & Kekre â€™ s Vector Quantization Algorithms Based Feature Extraction of Face & Iris,â€ pp. 29â€“34, 2011.
A. Aboshosha and K. A. El Dahshan, â€œScore Level Fusion for Fingerprint , Iris and Face Biometrics,â€ vol. 111, no. 4, pp. 47â€“55, 2015.
How to Cite
- Papers must be submitted on the understanding that they have not been published elsewhere (except in the form of an abstract or as part of a published lecture, review, or thesis) and are not currently under consideration by another journal published by any other publisher.
- It is also the authors responsibility to ensure that the articles emanating from a particular source are submitted with the necessary approval.
- The authors warrant that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required.
- The authors ensure that all the references carefully and they are accurate in the text as well as in the list of references (and vice versa).
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Attribution-NonCommercial 4.0 International that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
- The journal/publisher is not responsible for subsequent uses of the work. It is the author's responsibility to bring an infringement action if so desired by the author.