Authors Yu.A. Bryukhomitsky
Month, Year 09, 2016 @en
Index UDC 004.067
DOI 10.18522/2311-3103-2016-5057
Abstract The method of text-independent penscript online analysis is offered. It uses the principals of artificial immune systems functioning and is oriented on the task of personality verification by penscript. The method is based on using the immunological model of negative selection. The method can be used for analysis of any-size arbitrary text. A feature of the method is representation of information flows of the penscript in a form of the sequence of information units of the fixed format and size, with the following decentralized processing of them. For this purpose double quantization in time of initial information flows of the penscript is applied. Information units of penscript, in turn, are represented by vectors in multidimensional space of signs characterizing the position of the pen. The proposed method of verification of the penscript has several advantages. In comparison with the known method of online analysis of penscript based on frequency decomposition, suitable only for the analysis of strongly limited volumes of texts submitted by the predetermined words or short phrases, the offered method has no such restrictions, allowing analysis of arbitrary penscripts of any size. Due to a substantial expansion of volume of using hand-written data characterized features of the person the accuracy of analysis increases. The other fundamental difference of the offered immunological online analysis is the transition from the integrated evaluation of hand-written data by the fixed period of time to continuous evaluation of their temporal structure with the possibility of timely correct verification decision-making at rate of the hand-written data coming in. Such scheme of recognition gives advantages in solving the certain classes of tasks, which are critical to a time of adoption of the verification decision.

Download PDF

Keywords Text-independent penscript online analysis; personality verification by penscript; principles of artificial immune systems operation; vector representation of information units of penscript.
References 1. Govindan V K. Character recognition – a review, Pattern Recognition, 1990, Vol. 23, No. 7, pp. 671-683.
2. Sheybak A.N., Afanas'ev G.K. Razrabotka i analiz algoritmov identifikatsii pocherka [The de-velopment and analysis of algorithms for identification of handwriting], Informatsionnye tekhnologii, elektronnye pribory i sistemy ITEDS’2010: Materialy Mezhdunarodnoy nauchno-prakticheskoy konferentsii (6-7 aprelya 2010 g., Minsk) [Information technologies, electronic devices and systems ITEDS’2010: proceedings of the International scientific-practical confer-ence (April 6-7, 2010, Minsk)]. Minsk: Belorusskiy gosudarstvennyy universitet, 2010.
3. Tappert, C.C. The state of art in on-line handwriting recognition, IEEE Trans. Pattern Anal. Mach. Intell., 1990, Vol. 12, No. 8, pp. 787-808.
4. Nalwa V.S. Automatic On-Line Signature Verification, Proceedings of the IEEE, 1997,
Vol. 85, No. 2, pp. 215-2394.
5. Munich M. E., Perona P.Visual Signature Verification using Affine Arc-length, Conference on Computer Vision and Pattern Recognition CVPR, 1999, pp. 2180-2186.
6. Ivanov A.I. Biometricheskaya identifikatsiya lichnosti po dinamike podsoznatel'nykh dvizheniy [Biometric personal identification by dynamics of subconscious movements]. Penza: Izd-vo Penz. gos. un-ta, 2000, 188 p.
7. Bryukhomitskiy Yu.A., Kazarin M.N. Sistema autentifikatsii lichnosti po pocherku [The system of authenticating the identity of the handwriting], Sbornik trudov nauchno-prakticheskoy konferentsii s mezhdunarodnym uchastiem «Informatsionnaya bezopasnost'» [Proceedings of scientific-practical conference with international participation "Information security"]. Taganrog: Izd-vo TRTU, 2002, pp. 22-29.
8. Kolyadin D.V. Analiz dinamicheskikh krivykh primenitel'no k zadache verifikatsii rukopisnoy podpisi [Analysis of dynamic curves applied to the problem of handwritten signature verifica-tion], Matematicheskie metody raspoznavaniya obrazov (MMRO-11) [Mathematical methods of pattern recognition (MMPR-11)], 2003, pp. 330-332.
9. Lozhnikov P.S. Raspoznavanie dinamiki podpisi s ispol'zovaniem strategii Bayesa [The detection of the signature using a strategy Bayes], Doklady V Mezhdunar. konf. «Tsifrovaya obrabotka signalov i ee primenenie. DSPA-2003» [Reports of International conference "Digital signal processing and its application. DSPA-2003"]. Moscow: RNTORES im. A.S. Popova, 2003, Vol. 2, pp. 599-601.
10. Milykh V.A., Lapina T.I., Lapin D.V. Sposob biometricheskoy identifikatsii po pocherku v komp'yuterizirovannoy sisteme kontrolya dostupa [Method of biometric identification by handwriting in the computer, and-measured the system access control]. Patent RF
No. 2469397. 2012.
11. Dasgupta D. Artificial Immune Systems and Their Applications, Springer-Verlag, 1998.
12. De Castro L.N., Timmis, J.I. Artificial Immune Systems: A New Computational Intelligence Approach, London: Springer-Verlag 2000 September, 357 p.
13. Iskusstvennye immunnye sistemy i ikh primenenie [Artificial immune systems and their appli-cations], ed. by D. Dasgupty: from the English by A.A. Romanyukhi. Moscow: Fizmatlit, 2006, 344 p.
14. Bryukhomitskiy Yu.A. Immunologichekiy metod identifikatsii lichnosti po rukopisi [Immunotechnique metod of penscript analisis], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2015, No. 5 (166), pp. 174-183.
15. Forrest S., Perelson A.S., Allen L., Cherukuri R. Self-nonself discrimination in a computer, In: Proc. of Ieee symposium on research in security, Oakland, CA, 16-18 May 1994, pp. 202-212.
16. Dasgupta D., Forrest S. Tool breakage detection in milling operations using a negative-selection algorithm, Technical report CS95-5, Department of computer science, University of New Mexico, 1995.
17. Dasgupta D., Forrest S. Novelty detection in time series data using ideas from immunology, In: ISC A 5th international conference on intelligent systems, Reno, Nevada, June 19-21, 1996.
18. Dasgupta D., Yu S., Majumdar N. MILA – Multilevel Immune Learning Algorithm, Proceed-ings of the Genetic and Evolutionary Computation Conference – 2003, Springer – Verlag: Berlin Heidelberg, 2003, pp. 183-194.
19. Bryukhomitskiy Yu.A. Monitoring informatsionnykh protsessov metodami iskusstvennykh immunnykh sistem [Monitoring information processes methods of artificial immune system], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2012, No. 12 (137), pp. 82-90.
20. Bryukhomitskiy Yu.A. Model' adaptivnoy samoorganizuyushcheysya iskusstvennoy immunnoy sistemy dlya resheniya zadach komp'yuternoy bezopasnosti [Adaptive self-organizing artificial immune system model for a computer security particular purpose], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2013, No. 12 (149), pp. 63-69.
21. Bryukhomitskiy Yu.A. Immunologicheskiy podkhod k organizatsii klaviaturnogo monitoringa [The immunologic approach to keyboard monitoring organization], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2014, No. 2 (151), pp. 33-41.

Comments are closed.