Abstract
Modern access controls employ biometrics as a means of authentication to a great extent. For example, biometrics is used as an authentication mechanism implemented on commercial devices such as smartphones and laptops. This paper presents a fingerprint biometric cryptosystem based on the fuzzy commitment scheme and convolutional neural networks. One of its main contributions is a novel approach to automatic discretization of fingerprint texture descriptors, entirely based on a convolutional neural network, and designed to generate fixed-length templates. By converting templates into the binary domain, we developed the biometric cryptosystem that can be used in key-release systems or as a template protection mechanism in fingerprint matching biometric systems. The problem of biometric data variability is marginalized by applying the secure block-level Bose–Chaudhuri–Hocquenghem error correction codes, resistant to statistical-based attacks. The evaluation shows significant performance gains when compared to other texture-based fingerprint matching and biometric cryptosystems.
Highlights
Fingerprints are one of the most common biometric modalities used for authentication.There are three fingerprint matching approaches: correlation-based matching, minutiae-based matching, and non-minutiae feature-based matching
A binary BCH code consists of three parameters, n, k, t, where n is the length of the block and its value is defined as n = 2m−1, k is the length of the message being encoded, and t is the number of bits that can be corrected
We proposed a biometric cryptosystem scheme for authentication with template protection and biometric-dependent cryptographic key-release
Summary
Fingerprints are one of the most common biometric modalities used for authentication. Regardless of the feature extraction technique used, the design of biometric templates is generally driven by the following requirements for increasing the system security: nonreversibility (i.e., recovering the original sample from a given template must be computationally very expensive) [3], high-level performance (i.e., employed protection mechanisms should not affect the system accuracy), diversity (i.e., cross-matching across databases should not be feasible), and revocability (i.e., revoking a compromised template and generating a new one should be feasible) [1,4]. This requirement is not a limitation of the proposed system, since it is achieved in the context of commercial biometric systems
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
