R.A. Tomakova - Dr. Sc. (Eng.), Professor, Department of Software Engineering, South-West State University, Kursk M.V. Tomakov - Ph.D. (Eng.), Associate Professor, Department of Occupational and Environmental, South-West State University, Kursk I.V. Durakov - Head of the Department of Radiological Studies, Emergency Hospital, Kursk V.V. Zhilin - Ph.D. (Eng.), Associate Professor, Department of Higher and Applied Mathematics, Kursk State Agricultural Academy

The urgency in the development of methods designed for intelligent systems classification of complex-structured images occurs in the processing of X-ray images of medical images. The intellectual system for automatic classification of complex-structured images, which is based on the classification method based on X-ray studies of the global information about the structure of the processed images. Computer technologies are focused on rapid decision-making, which is achieved through the implementation of a distributed data processing in the cellular structure of the image. A feature of the proposed approach is to use two classifiers implementing two methods of classification. The first classifier performs a portion of the image that has entered the cell, and the second carries texture analysis. The contradiction between the classification accuracy and computational resources offered to solve through the use of a distributed computing system. A block diagram of an intelligent system of classification slozhnostrukturiruemyh image, which is presented in the article below. To implement these two methods of analysis and classification of images is provided a block of processors. Each processor unit that is associated with his image cell. It should be noted that the structure of the processor block adapts to image cells, the image cells and formatted by the results of the classifiers. Thus, in the presence of mathematical and algorithmic machine topology modeling and anatomical objects on X-ray there is an available recovery algorithm shaded morphological formations. The study was financially supported by RFBR in the framework of a research project and number 16-07-00164.

 

1. Filist S.A., Djudin M.V., Zuev I.V. i dr. Avtomaticheskie klassifikatory slozhnostrukturiruemykh izobrazhenijj na osnove multimetodnykh tekhnologijj mnogokriterialnogo vybora // Voprosy radioehlektroniki. Ser. Sistemy i sredstva otobrazhenija informacii i upravlenija spectekhnikojj. 2015. Vyp. 1. S. 130-140.
2. Djudin M.V., ZHilin V.V., Kudrjavcev P.S. i dr. Sposob vydelenija kontura izobrazhenija legkikh na rentgenovskom snimke grudnojj kletki // Izvestija JUgo-Zapadno­go gosudarstvennogo universiteta. Ser. Upravlenie, vychislitelnaja tekhnika, informatika. Medicinskoe priborostroenie. 2014. № 4. S. 107-114.
3. Tomakova R.A., Efremov M.A., Filist S.A., SHatalova O.V. Gibridnye tekhnologii vydelenija medlennykh voln iz kvaziperiodicheskikh signalov // Izvestija JUgo-Zapadnogo gosudarstvennogo universiteta. 2011. № 1(34). S. 66-73.
4. Akimov A.V., Sirota A.A. Razrabotka i issledovanie algoritmov raspoznavanija izobrazhenijj na osnove metoda Violy-Dzhonsa s ispolzovaniem tekhnologii vychislenijj na graficheskikh processorakh Cuda // Vestnik VGU. Ser. Sistemnyjj analiz i informacionnye tekhnologii. 2014. № 3. S. 105-108.
5. Tomakova R.A., Filist S.A., Emeljanov S.G. Teoreticheskie osnovy i metody obrabotki i analiza mikroskopicheskikh izobrazhenijj biomaterialov. Kursk: JUgo-Zap. gos. un-t. 2011. 202 s.
6. Djudin M.V., Filist S.A., Kudrjavcev P.S. Sposob vydelenija i klassifikacii konturov legkikh na izobrazhenijakh fljuorogramm grudnojj kletki // Naukoemkie tekhnologii. 2014. T. 15. № 12. S. 25-30.
7. Ivanov A.V., Tomakova R.A., Mishustin V.N. Intellektualnaja sistema morfologicheskogo analiza patologicheskikh izmenenijj pri retinopatii // Izvestija JUgo-Za­padnogo gosudarstvennogo universiteta. 2012. № 2-1(41).  S. 19-27.
8. Tomakova R.A., Filist S.A. Metod obrabotki i analiza slozhnostrukturiruemykh izobrazhenijj na osnove vstroennykh funkcijj sredy MATLAB // Vestnik CHitinskogo gosudarstvennogo universiteta. 2012. № 1(80). S. 3-9.
9. Tomakova R.A. Proektirovanie gibridnojj nejjronnojj seti dlja analiza slozhnostrukturirovannykh medicinskikh izobrazhenijj // Sistemnyjj analiz i upravlenie v biomedicinskikh sistemakh. 2011. T. 10. № 4. S. 916-923.
10. Kazakovcev L.A., Antamoshkin A.N. Metod zhadnykh ehvristik dlja zadach razmeshhenija // Vestnik SibGAU. 2015. № 2. S. 317-325.
11. Degtjarev S.V., Filist S.A., Djudin M.V. Mnogoagentnyjj podkhod postroenija sistemy intellektualnojj podderzhki prinjatija reshenijj analiza i klassifikacii fljuorogramm // Biomedicinskaja radioehlektronika. 2014. № 9. S. 17-21.