Informatics and Applications
2014, Volume 8, Issue 3, pp 45-52MODELS FOR COMPARATIVE ANALYSIS OF CLASSIFICATION METHODS IN DISTRIBUTED OBJECT RECOGNITION SYSTEMS
- Ya. M. Agalarov
Abstract
The paper considers recognition systems where classes are defined by appropriate patterns located in distributed data base. Recognition criterion is full coincidence of the presented sample with at least one of the patterns. Parallel and sequential classification methods are compared in terms of mean response time to recognition request and performance requirements. The results of numerical experiments which were carried out for multibiometric recognition systems using analytical and simulation models of queueing networks are presented.[+] References (12)
- Tel, G. 1995. Introduction to distributed algorithms. Cam-bridge: Cambridge University Press. 546 p.
- Gorelik, A. L., and V. A. Skripkin. 2004. Metody raspoz- navaniya [Methods of recognition]. Moscow: Vysshaya Shkola. 261 p.
- Khrulev, A. 2012. Sistemy raspoznavaniya lits. Sostoyanie rynka. Perspektivy razvitiya [Face recognition systems. State of the market. Prospects of development]. Sistemy Bezopasnosti [Security Systems] 1:70-72.
- Babenko, L. K., E. A. Ishchukova, andI. D. Sidorov. 2012. Parallel'nye vychisleniya v kriptoanalize [Parallel computation in cryptanalysis]. Izvestiya YuFU. Tekhnicheskie Nauki [Gerald of South Federal University. Engineering Sciences] 12(137):148-157.
- Murynin, A. B., D. V. Kovkov, V. V. Lobantsov, K. A. Makovkin, I. A. Matveev, D. D. Desyatnikov, and V. Ya. Chuchupal. 2006. Mul'timodal'naya biometriya - perspektivnoe reshenie. Ob"edinenie algoritmov dlya povysheniya nadezhnosti raspoznavaniya cheloveka [Multimodal biometrics is a promising solution. Merging algorithms to improve the reliability of recognition of a person]. Sistemy Bezopasnosti [Security Systems] 6:156-160.
- Ushmaev, O. S., and A.V Bosov. 2008. Realizatsiya kontseptsii mnogofaktornoy biometricheskoy identifikatsii v integrirovannykh analiticheskikh sistemakh [Implementation of multimodal biometrics for integrated analytics]. Biznes i Bezopasnost' v Rossii [Business and Security in Russia] 49:104-105.
- Ushmaev, O. S. 2009. Problemyrasparallelivaniyabiomet- richeskikh vychisleniy v krupnomasshtabnykh identifikat- sionnykh sistemakh [Parallel computing in large-scale multimodal biometric systems]. Informatika i ee Prime-neniya - Inform. Appl. 3(1):8-18.
- Smirnov, S.V 2012. Podsistema massovogo raspozna- vaniya izobrazheniy arkhivnykh dokumentov [Subsystem of mass image recognition of archival documents]. Tr. SPIIRAN [SPIIRAS Proceedings] 3(22):234-246.
- Hunt, E. B. 1975. Artificial intelligence. New York: Aca-demic Press. 468 p.
- Tamer Ezsu, M., and P. Valduriez. 1996. Raspredelennye i parallel'nye sistemy baz dannykh [Distributed and parallel database systems]. Sistemy Upravleniya Bazami Dan- nykh [Databases Management Systems] 4. Available at: http://www.osp.ru/dbms/1996/04/13031501 (accessed July 8, 2014).
- Kleinrock, L. 1976. Queueing systems: Volume II - Com-puter Applications. New York: Wiley Interscience. 576 p.
- Korn, G. A., and T. M. Korn. 1961. Mathematical hand-book for scientists and engineers. New York: McGraw-Hill Book Co. 943 p.
[+] About this article
Title
MODELS FOR COMPARATIVE ANALYSIS OF CLASSIFICATION METHODS IN DISTRIBUTED OBJECT RECOGNITION SYSTEMSJournal
Informatics and Applications2014, Volume 8, Issue 3, pp 45-52
Cover Date
2014-03-31DOI
10.14357/19922264140306Print ISSN
1992-2264Publisher
Institute of Informatics Problems, Russian Academy of SciencesAdditional Links
Key words
distributed recognition system; parallel and sequential classification methods; resource allocation; queueing networkAuthors
Ya. M. Agalarov
Author Affiliations
Institute of Informatics Problems, Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119333, Russian
Federation