To obtain access to full text of journal and articles you must register!
- Article name
- Verification of authenticity for handwritten signatures using Bayesian-Hamming networks and quadric form networks
- Authors
- Lozhnikov P. S., , lozhnikov@gmail.com, Omsk State Technical University, Omsk, Russia
Ivanov A. I., , ivan@pniei.penza.ru, Penza Research Electrotechnical Institute, Penza, Russia
Kachajkin E. I., , kachajkin@gmail.com, Ministry of Justice of the Russian Federation, Moscow, Russia
- Keywords
- Bayesian-Hamming networks / quadric form networks / Pearson-Hamming neural networks / evaluation of type 1 and type 2 errors
- Year
- 2015 Issue 2 Pages 28 - 34
- Code EDN
- Code DOI
- Abstract
- The paper describes the issue of network translation of handwritten signature biometric parameters into a long access code that may be used as a login. A personal signature is used quite often so it should be considered as an open biometric image. The biometric parameters of a signatures are impossible to conceal therefore Bayesian-Hamming networks and quadric form networks may be used for personal identification. The paper proposes a method to evaluate the potential advantages of using Bayesian-Hamming networks, quadric form networks and other networks that take into account a high level of correlation for biometric data of a Friend image. The comparison is made via Pearson-Hamming RBF artificial neural networks that totally disregard correlation relationship of biometric data.
- Text
- To obtain access to full text of journal and articles you must register!
- Buy
