BIOMETRIC IDENTIFICATION OF A PERSON BY SEVERAL PARAMETERS

The article is devoted to the development of a system of biometric identification of a person by face, fingerprints and voice. Two-dimensional and three-dimensional characteristics of a person's face, taking into account area and volume, were used as informative signs of biometric identification of a person by face. A complex identification algorithm has been developed to account for such phenomena as portrait shift, different photo scales, and the tilt of the identified face. The FPM10A scanner and the Arduino microcontroller are used for biometric identification of a person by fingerprints.

Identification signs are based on the analysis of the structure of papillary patterns on the finger: type and type of papillary pattern; direction and steepness of streams of papillary lines; the structure of the central pattern of the pattern; delta structure; the number of papillary lines between the center and the delta and many other signs. Another type of feature is local. They are also called minutiae (features or special points) — unique features inherent only in a particular print, determining the points of change in the structure of papillary lines (end, split, break, etc.), the orientation of papillary lines and coordinates at these points. Each print can contain up to 70 or more minutations.

For biometric identification of a person by voice, MFC and PLP algorithms for digital processing and analysis of audio recordings are used. Various algorithms are used for acoustic speech analysis: hidden Markov models, a model of a mixture of Gaussian distributions. The result of determining the tone of speech and the content of speech for the purposes of voice identification is obtained.

The Visual FoxPro DBMS has developed a «multiparametric automated system for biometric identification of an individual».

1. G.A. Buzov. Practical guide to identifying special technical means of unauthorized obtaining of information. – М.: Hot line – Telecom, 2010. – 240 p.

2. U.F. Katorin, A.V. Razumovskiy, A.Y. Spivak. Protection of information by technical means. Saint Petersburg: NRU ITMO, 2012. – 416 p.

3. R.M. Bolle, J.H. Connel, S. Pankanti, N.K. Ratha, A.W. Senior. Guide to Biometrics, SprinterVerlag New York, 2004.

4. S. Crihalmeanu, A. Ross. Multispectral sclera patterns for ocular biometric recognition, Pattern Recognition. Lett. 33 (2012)1860–1869.

5. V.B. Klepinin, T.P. Agafonov. Visual FoxPro 9.0. The most complete guide. – Saint Petersburg.: BHV-Petersburg, 2007. – 1216 p.

6. S. A. Ayvazyan, V. M. Buchberger, I. S. Enyukov, L. D. Meshalkin. Applied statistics. Classification and dimensionality reduction. – М.: Finance and statistics, 1989. – 607 p.

7. V. A. Petin. Projects using the Arduino controller. – Saint Petersburg.: BHV-Petersburg, 2016. – 464 p.

8. Tan and B. Bhanu. Robust fingerprint identification, in International Conference on Image Processing 2002. – Vol. 1. – IEEE. Р. 1-277.

9. Ethan Rublee, Vincent Rabaud, Kurt Konolige, Gary Bradski: «ORB: an efficient alternative to SIFT or SURF», Computer Vision (ICCV), IEEE International Conference on IEEE, 2011. – Р. 2564-2571.

10. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. Neural machine translation by jointly learning to align and translate. CoRR, abs/1409.0473, 2014.