D.V. Lapin - Research Scientist, Kursk research institute of Defence Ministry. E-mail: lapindv@mail.ru F.A. Starkov - Ph. D. (Phys.-Math.), Professor, Southwest State University (Kursk)

In this article approach to creation of system of dynamic biometric authentication of users on hand-written handwriting when performing operations in computer networks is considered. For data input of the biometric control the gauge of movings is used multicomponent. For the organization of input of the biometric data of the user the gage of movings is used multicomponent. Transformation of a multichannel analog signal of the gage to a multichannel discrete signal in the form of a matrix quantum readout is carried out. As a result of transformation receive a matrix of factors two-dimensional discrete transformations of Haar wavelet which is used as identification parametres for authentification. Database of users allowed to access the system is formed from discretised and quantised readings of samples of the handwriting of a matrix of two-dimensional discrete cosine transform (TDCT) coefficients. When allowing a new user into the system, a matrix of TDCT coefficients similar to the reference sample is formed from the discretised and quantised readings of samples of the handwriting of that user. Comparison is carried out and a decision is made to associate the obtained record to one of the reference records. Signal decomposition on n of the directions of movement allows to make the analysis of everyone fragment of decomposition of a signal that simplifies a problem of a marking and the analysis of an initial image. The offered way of dynamic biometric authentification of the user on the hand-written doesn\'t demand expensive input readers of the biometric information, allows to change the password and can supplement other biometric systems of authentification.

 

1. Lapina T.I., Milykh V.A., Lapin D.V. Sposob biometricheskojj autentifikacii polzovatelja po rukopisnomu pocherku v sistemakh kontrolja dostupa // Informacionno-izmeritelnye i upravljajushhie sistemy. 2011. T. 9. № 11. S. 40−43.
2. Lapina T.I., Petrik E.A., Lapin D.V. Postroenie biometricheskikh sistem kontrolja i upravlenija dostupom po rukopisnomu pocherku // Naukoemkie tekhnologii. 2012. T. 13. № 8. S. 10−12.
3. Pat. № 2500986. MPK Cifrovojj mnogokomponentnyjj datchik peremeshhenijj / Milykh V.A., Lapina T.I., Lapin D.V. Zajavka 2011148314/28 ot 28.11.2011. Opubl. 10.12.2013. Bjul. № 34.
4. Pat. № 469397 MPK G06K9/00. Sposob biometricheskojj autentifikacii po pocherku v kompjuterizirovannykh sistemakh kontrolja dostupa / Milykh V.A., Lapina T.I., Lapin D.V. Zajavka № 2011140031/08, 30.09.2011. Opubl. 10.12.2012.Bjul.№ 34.
5. Maged M.M. Fahmy Online handwritten signature verification system based on DWT features extraction and neural network classification // Ain Shams Engineering Journal. September 2010. Vol. 1. № 1. P. 59−70.
6. Pradeep Kumar, Shekhar Singh Ashwani, Garg Nishant Prabhat Hand Written Signature Recognition & Verification using Neural Network // International Journal of Advanced Research in Computer Science and Software Engineering. March 2013. V. 3. № 3.
7. Prashanth C.R., Raja K.B., Venugopal K.R., Patnaik L.M. DWT based Offline Signature Verification using Angular Features // International Journal of Computer Applications. August 2012. № 52(15). P. 40−48. Published by Foundation of Computer Science, New York, USA.
8. Olaf Henniger, Sascha Müller Handwritten Signature On-Card Matching Performance Testing. Biometric ID Management and Multimodal Communication // Lecture Notes in Computer Science. 2009. V. 5707. P. 268−275.