To obtain access to full text of journal and articles you must register!
- Article name
- Biometric identification of handwritten images via correlation analog of Bayes' rule
- Authors
- Lozhnikov P. S., , lozhnikov@gmail.com, Omsk State Technical University, Omsk, Russia
Sulavko A. E., , sulavich@mail.ru, 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
- Bayes' rule / multivariate statistical analysis / multivariate correlation coefficients
- Year
- 2015 Issue 3 Pages 48 - 54
- Code EDN
- Code DOI
- Abstract
- In article considered biometric identification by using handwriting characteristics of a keyword or an autograph. It is shown that Bayes' rule is effective in the case of high correlation biometric handwriting image. By analogy with the metric chi-square Pearson introduced the metric Bayes-Pearson that is sensitive to correlation relations of identifiable biometric image. Computational simplicity of the proposed method caused by the fact that in the space of metrics Bayes-Pearson takes symmetrization of multivariate statistical description of the object identification (handwriting image).
- Text
- To obtain access to full text of journal and articles you must register!
- Buy
