Computerized recognition of fundamental electrical circuits of railway automation and remote control (RARC) is an urgent and diffi cult task. The decision can be reasonably divided into the decision of the individual sub-tasks. Thus, the general recognition algorithm is divided into several specialized algorithms and the decision becomes more simple and straightforward. The main sub-tasks are selection and recognition of the fundamental electrical circuits structure, of the text, of the stamp and of other information. The article describes an approach for structure selection of the fundamental electrical circuits of RARC.Methods of selection of circuit structure, proposed in this article, do not solve the problem of the complete recognition of the structure of fundamental electrical circuit with definition of elements and arrangement of connections between them, the solution of which requires much more profound and time-consuming analysis. However, the task of separating the graphic structure from the rest of the circuit information is a preparatory and necessary to further recognition process.The article proposes a modifi cation of a known algorithm for creating the skeleton of an image Zhang-Suen for recognition of existing printed and handwritten fundamental electric circuits of RARC. It also considers the methods of image pre-processing, as well as the selection of minimum required set of pre-processing algorithms. The article provides an example of a fragment of an actual fundamental electric circuit, as well as a conclusion about possibility of implementation of system for further recognition on the basis of a selected structure.
electronic document management, technical documentation, image recognition, fundamental electrical circuits, selection of circuit skeleton
1. Vasilenko M. N. Elektronnyy dokumentooborot v hozyaystve SCB / M. N. Vasilenko, V. G. Trohov, D. V. Zuev // Avtomatika svyaz', informatika. - 2014. - № 8. - S. 2-3.
2. Bulavskiy P. E. Elektronnyy dokumentooborot tehnicheskoy dokumentacii / P. E. Bulavskiy, D. S. Markov // Avtomatika, svyaz', informatika. - 2012. - № 2. - S. 2-5.
3. Bulavskiy P. E Sintez formalizovannoy shemy elektronnogo dokumentooborota sistem zheleznodorozhnoy avtomatiki i telemehaniki / P. E. Bulavskiy, D. S. Markov // Izvestiya Peterburgskogo universiteta putey soobscheniya. - 2013. - № 2. - S. 108-115.
4. Bursian E. Yu. Raspoznavanie tablic montazhnyh kartochek tehnicheskoy zheleznodorozhnoy dokumentaciii / E. Yu. Bursian // Izvestiya Peterburgskogo universiteta putey soobscheniya. - 2010. - № 2. - S. 137-145.
5. Bursian E. Yu. Postroenie baz dannyh etalonnyh simvolov pri avtomaticheskom raspoznavanii testov / E. Yu. Bursian // Izvestiya Peterburgskogo universiteta putey soobscheniya. - 2015. - № 4. - S. 93-100.
6. Baluev N. N. Problemy vnedreniya otraslevogo formata / N. N. Baluev, M. N. Vasilenko, V. G. Trohov, D. V. Sedyh //Avtomatika, svyaz', informatika. - 2010. - № 3. - S. 2.
7. Matushev A. A. Raspoznavanie struktury montazhnyh shem ZhAT / A. A. Matushev, D. V. Sedyh // Avtomatika, svyaz', informatika. - 2015. - № 10. - S. 4-7.
8. Sedyh D. V. Metody raspoznavaniya struktury montazhnyh shem zheleznodorozhnoy avtomatiki i telemehaniki / D. V. Sedyh, A. A. Matushev // Avtomatika na transporte. - 2016. - T. 2. - № 4. - S. 552-563.
9. Vasilenko M. N. Metody vydeleniya tekstovyh vyrazheniy principial'nyh elektricheskih shem zheleznodorozhnoy avtomatiki i telemehaniki / M. N. Vasilenko, R. A. Kovalev // Avtomatika na transporte. - 2016. - T. 2. - № 4. - S. 540-551.
10. Zuev D. V. Sintez ob'ektnoy neyrosetevoy modeli raspoznavaniya obrazov i ee primenenie v zadachah zheleznodorozhnoy avtomatiki : dis. … kand. tehn. nauk : 05.13.18 / Zuev Denis Vladimirovich. - SPb., 2013. - 122 s. : il.
11. Kvasnikov V. P. Uluchshenie vizual'nogo kachestva cifrovogo izobrazheniya putem poelementnogo preobrazovaniya / V. P. Kvasnikov, A. V. Dzyubanenko // Aviacionno-kosmicheskaya tehnika i tehnologiya. - 2009. - № 8. - S. 200-204.
12. Milewski R., Govindaraju V. Binarization and cleanup of handwritten text from carbon copy medical form images (31 March 2008) / R. Milewski, V. Govindaraju // Pattern Recognition. - Vol. 41, issue 4. - Pp. 1308-1315.
13. Ester M. A density-based algorithm for discovering clusters in large spatial databases with noise / M. Ester, H.-Pe. Kriegel, J. Sander, X. Xu, E. Simoudis, J. Han, U. M. Fay- yad // Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD-96). - AAAI Press, 1996. - Rr. 226-231.
14. Tu Dzh. Principy raspoznavaniya obrazov / Dzh. Tu, R. Gonsales. - M. : Mir, 1978. - S. 109-112.
15. Frey B. J., Dueck D. (2007). Clustering by passing messages between data points. - Vol. 315. - Pp. 972-976.
16. Online magazine «Image Processing and Computer Vision», A Fast Parallel Algorithm for Thinning Digital Patterns. - URL : http://www-prima.inrialpes.fr/perso/Tran/ Draft/gateway.cfm.pdf.
