Main Article Content
The subject of this research is the image classification methods based on a set of key points descriptors. The goal is to increase the performance of classification methods, in particular, to improve the time characteristics of classification by introducing hashing tools for reference data representation. Methods used: ORB detector and descriptors, data hashing tools, search methods in data arrays, metrics-based apparatus for determining the relevance of vectors, software modeling. The obtained results: developed an effective method of image classification based on the introduction of high-speed search using hash structures, which speeds up the calculation dozens of times; the classification time for the considered experimental descriptions increases linearly with decreasing number of hashes; the minimum metric value limit choice on setting the class for object descriptors significantly affects the accuracy of classification; the choice of such limit can be optimized for fixed samples databases; the experimentally achieved accuracy of classification indicates the efficiency of the proposed method based on data hashing. The practical significance of the work is - the classification model’s synthesis in the hash data representations space, efficiency proof of the proposed classifiers modifications on image examples, development of applied software models implementing the proposed classification methods in computer vision systems.
Kleinrock, L. (1979), Queuing Theory, Mechanical Engineering, Moscow, 330 p.
Kleinrock, L. (1979), Computing networks with queues, Mir, Moscow, 406 pp.
Kofman, A. and Kruon, R. (1965), Mass Service (Theory and Applications), Mir, Moscow, 302 pp.
Aven, O.I., Gurin, N.N. and Kogan, Ya.A. (1982), Assessment of the quality and optimization of computing systems, Nauka, Moscow, 132 pp.
Porotsky, S. (2000), “Modeling the routing algorithm of the transport ATM network”, Electrosvyaz, no. 10, pp. 16-19.
Turko, S.A., Fomin, L.A., Budko, P.A., Zdanevich, S.N. and Gakhova, N.N. (2002), “Optimization of the bandwidth of SH-ISDN links with limited network resources”, Electrosvyaz, No. 2, pp. 17-19.
Yabnykh, G.A. and Stolyarov, B.A. (1987), Optimization of information computer networks, Radio i svyaz, Moscow, 230 p.
Yakubaitis, E.A. (1984), Information computing networks, Finance and statistics, Moscow, 310 p.
Budko, P.A. (2000), “The choice of channel capacities in the synthesis of a communication network under changing load conditions”, Physics of wave processes and radio engineering systems, Vol. 3, No. 3-4, pp. 68-72.
Mizin, I.A., Bogatyrev, V.A. and Kuleshov, A.P. (1986), Packet Switching Networks, Radio i svyaz, Moscow, 408 p.
Morozov, V.K. and Dolganov, A.V. (1987), Fundamentals of the theory of information networks, Vysshaya Shkola, Moscow, 271 p.
Budko, P.A. and Fedorenko, V.V. (2003), Management in communication networks. Mathematical models and opti-mization methods,:Izd. physico-mathematical literature, Moscow, 228 p.
Pasechnikov, I.I. (2004), Methodology for analysis and synthesis of extremely loaded information networks, Machine building-1, Moscow, 216 p.