|
This article is cited in 20 scientific papers (total in 20 papers)
NUMERICAL METHODS AND DATA ANALYSIS
Evaluation of signature verification reliability based on artificial neural networks, Bayesian multivariate functional and quadratic forms
A. I. Ivanova, P. S. Lozhnikovb, A. E. Sulavkob a Penza Scientific and Research Electrotechnical Institute, Penza, Russia
b Omsk State Technical University, Omsk, Russia
Abstract:
An experimental comparison of various functional neural networks for signature verification is performed. A signature database for the realization of the computing experiment is built. It is confirmed that up to a certain point, the increase of the decision rule dimension reduces the probability of signature verification error, with an increase in the number of neurons in the network reducing the number of errors. A higher-dimension multi-dimensional Bayes functional with stronger inter-feature correlation is found to perform better. The best result for the signature verification is obtained using networks of Bayesian multidimensional functional, with false acceptance rate of $FRR = 0.0288$ and false rejection rate of $FAR = 0.0232$.
Keywords:
neural networks, network of quadratic forms, multi-dimensional Bayes functional, signature reproduction peculiarities, biometric features.
Received: 29.05.2017 Accepted: 21.08.2017
Citation:
A. I. Ivanov, P. S. Lozhnikov, A. E. Sulavko, “Evaluation of signature verification reliability based on artificial neural networks, Bayesian multivariate functional and quadratic forms”, Computer Optics, 41:5 (2017), 765–774
Linking options:
https://www.mathnet.ru/eng/co447 https://www.mathnet.ru/eng/co/v41/i5/p765
|
|