A biometric encryption approach incorporating fingerprint indexing in key generation

Authors:
Fengling Han;Jiankun Hu;Xinghuo Yu
Affiliations:
Science, Engineering and Technology Portfolio, Royal Melbourne Institute of Technology, Melbourne, VIC, Australia;Science, Engineering and Technology Portfolio, Royal Melbourne Institute of Technology, Melbourne, VIC, Australia;Science, Engineering and Technology Portfolio, Royal Melbourne Institute of Technology, Melbourne, VIC, Australia
Venue:
ICIC'06 Proceedings of the 2006 international conference on Computational Intelligence and Bioinformatics - Volume Part III
Year:
2006

Citing 8
Cited 2

A Real-Time Matching System for Large Fingerprint Databases

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Multichannel Approach to Fingerprint Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fingerprint Indexing Based on Novel Features of Minutiae Triplets

IEEE Transactions on Pattern Analysis and Machine Intelligence
Handbook of Fingerprint Recognition

Handbook of Fingerprint Recognition
Fingerprint Classification by Directional Fields

ICMI '02 Proceedings of the 4th IEEE International Conference on Multimodal Interfaces
Fingerprint Identification: Classification vs. Indexing

AVSS '03 Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance
Fingerprint classification based on learned features

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Filterbank-based fingerprint matching

IEEE Transactions on Image Processing

Information Assurance: Dependability and Security in Networked Systems

Information Assurance: Dependability and Security in Networked Systems
Seamless integration of dependability and security concepts in SOA: A feedback control system based framework and taxonomy

Journal of Network and Computer Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new biometric encryption protocol in which encryption key is incorporated with fingerprint indexing. Based on the extended chaotic Baker map, the pixel permutation and gray level value substitution are performed to shuffle pixel positions in the original fingerprint images. The encryption key of the pixel permutation is generated by the combination of the random pixel distribution of a fingerprint imprint as well as features used for the fingerprint indexing. In addition to the advantage enjoyed by biometric keys over traditional password/PINs, the proposed biometric encryption approach is very efficient in identity identification within a large database due to the pre-filtering feature of the fingerprint indexing incorporated in the keys. This approach is applicable to the centralized matching scenario where fingerprints need to be encrypted before transmitted. Simulation results have validated the proposed schemes.