Experimental Evaluation of Reliability of Signature Verification by Quadratic Form Networks, Fuzzy Extractors and Perceptrons
Abstract
Purpose: The problems of information security become more and more pressing, therefore the demands to biometric systems become tougher. Our objective is to compare fuzzy extractors, neural network biometry-code converters and networks of quadratic forms by their authentication reliability, on the base of signature features. Results: We have analyzed the literature and conducted a series of numerical experiments based on real biometric data. The main result of the experiments is that fuzzy extractors are significantly inferior to the other system by their authentication reliability and the key length. The best performance was provided by Bayesian- Pearson networks. Practical relevance: The results will be of interest to researchers and developers of biometric systems.Published
2016-10-21
How to Cite
Lozhnikov, P., Sulavko, A., Eremenko, A., & Volkov, D. (2016). Experimental Evaluation of Reliability of Signature Verification by Quadratic Form Networks, Fuzzy Extractors and Perceptrons. Information and Control Systems, (5), 73-85. https://doi.org/10.15217/issn1684-8853.2016.5.73
Issue
Section
Information coding and transmission