INFORMATION TECHNOLOGIES IN THEORY RECOGNITION OF IMAGES. METHOD OF CONSTRUCTING MODELS AT SCENE ANALYSIS
DOI:
https://doi.org/10.32782/KNTU2618-0340/2020.3.2-1.22Keywords:
information; information space; recognition system; fuzzy set; information flowAbstract
Pattern recognition is perhaps one of the most widely covered information technology problems in the literature. A multitude of methods and successful solutions created a motley picture of the "complexity" of the problem. At the same time, attention should be paid to the fact that we are dealing with information technology - methods and means of information processing. Information theory differs in that there is a mass of interpretations of the content of the concept of information. This is uncertainty, and the number of symbols and the expected impact, where each of the authors, solving some of his own problem, gave his own definition of the content of this concept. Moreover, the process of building recognition systems always requires a general approach to the synthesis of algorithms and methods. This work is devoted to the development of theoretical methods of information theory in relation to the problem of creating information systems for pattern recognition. The work is based on a correspondence mechanism, which allows relying on the generality of the results obtained. The main goal of the work is to supplement the approaches and formalization to the construction of models of the processes of receiving, transferring, processing and storing information in the information space. Based on the analysis of the pattern recognition system in the information space, the work considers general approaches to the construction of pattern recognition algorithms. One of the main results of the work is the substantiation and demonstration of the effectiveness of information space methods, the use of general correspondence methods and general principles. In particular, the principle of irreversibility of time and the principle of optimality, which allow us to assume that mathematical models and algorithms in the information space have the property of generality. An example of solving the recognition problem in the implementation of a scene analysis system is considered, which shows methods for synthesizing the system's algorithm and the independence of the information structure of the system from the methods and levels of implementation of the system for compensating information flows.
References
Zhang H., Li D. Applications of Computer Vision Techniques to Cotton Foreign Matter Inspection: A Review. Computers and Electronics in Agriculture. 2014. Vol. 109. P. 59–70. DOI: 10.1016/j.compag.2014.09.004.
Tadhg B., Sun Da-Wen. Inspection and Grading of Agricultural and Food Products by Computer Vision Systems: A Review. Computers and Electronics in Agriculture. 2002. Vol. 36. Issue 2−3. P. 193−213. DOI: 10.1016/S0168-1699(02)00101-1.
Wenzhu Yang et al. A New Approach for Image Processing in Foreign Fiber Detection. Computers and Electronics in Agriculture. 2009. Vol. 68. Issue 1. P. 68–77. DOI: 10.1016/j.compag.2009.04.005
Yang W., Li D., Wei X., et al. An Automated Visual Inspection System for Foreign Fiber Detection in Lint. 2009 WRI Global Congress on Intelligent Systems. Vol. 4.(China, Xia Men, May 19–21 2009). P. 364–368.
Yang W., Li D., Wang S., Lu S., et al. Saliency-Based Color Image Segmentation in Foreign Fiber Detection. Mathematical and Computer Modelling. 2013. Vol. 58. Issue 3−4. P. 852–858.
Zhao X., Li D., Yang W., et al. Feature Selection for Cotton Foreign Fiber Objects Based on Improved and Colony Algorithm. Nongye Jixie Xuebao/Transactions of the Chinese Society of Agricultural Machinery. 2011. Vol. 42. Issue 4. P. 168–173. (in Chinese with English abstract).
Wang R., Liu S., Wang Q., et al. Classification Features of Feather and Hemp in Cotton Foreign Fibers. Nongye Jixie Xuebao/Transactions of the Chinese Society of Agricultural Machinery. 2012. Vol. 28. Issue 2. P. 202–207.
Russakovsky O., Deng J., Su H., et al. Image NET large scale visual recognition challenge. International Journal of Computer Vision. 2015. Vol. 115. Issue 3. P. 211–252.
Fine T. L. Feedforward Neural Network Methodology. Berlin: Springer Science Business Media, 2006. 356 p.
Ramesh B., Bhardwaj A., Richardson J., et al. Optimization and Evaluation of Imageand Signal-Processing Kernels on the TI C6678 Multi-Core DSP. IEEE High Performance Extreme Computing Conference (HPEC). (USA, Waltham, September 9–11, 2014). 6 p.
Hartley R. V. L. Transmission of Information. Bell System Technical Journal. 1928. Vol. 7. Issue 3. P. 535−563.
Sokolov A. Sokolova O. Solving the Task of Measuring Information Quantity through Model Identification with Minimization of the Estimation Error. Проблемиінформаційних технологій. 2016. № 2(20). C. 56−62.
Gonzalez R. C., Woods R. E., Eddins S. L. Digital Image Processing Using MATLAB. Pearson Prentice-Hall, 2004. 609 p.
Pratt W. K. Introduction to Digital Image Processing. Boca Raton: CRC Press Taylor & Francis Group, 2013. 756 p.
Тимофеев А. В. Адаптивные робототехнические комплексы. Л.: Машиностроение, 1988. 332 с.
Стратонович Р. Л. Теория информации. М.: Сов. радио, 1975. 424 с.
Колмогоров А. Н. Теория информации и теория алгоритмов. М.: Наука, 1987. 304 с.
Шеннон К. Работы по теории информации и кибернетике. М.: Издательство иностранной литературы, 1963. 824 с.
Huang T. S. (Ed.) Image Sequence Processing and Dynamic Scene Analysis. Berlin: Springer, 1983. 759 p. 20. Ту Дж., Гонсалес Р. Принципы распознавания образов. М.: Мир, 1978. 412 c.
Гренадер У. Лекции по теории образов: Анализ образов. Т. 2. Пер. с англ. М.: Мир, 1981. 488 с.
Soares A. M., Fernandes B. J. T., Bastos-Filho C. J. A. Pyramidal Neural Networks with Evolved Variable Receptive Fields. Neural Computing and Applications. 2016. Vol. 29. Issue 12. P. 1443–1453. DOI:10.1007/s00521-016-2656-2.
Bottou L. Large-Scale Machine Learning with Stochastic Gradient Descent. COMPSTAT’2010: 19th International Conference on Computational Statistics (France, Paris, August 22-27, 2010). Paris: Springer, 2010. P. 177–186.
Ramesh B., Bhardwaj A., Richardson J., et al. Optimization and Evaluation of Imageand Signal-Processing Kernels on the TI C6678 multi-core DSP. IEEE High Performance Extreme Computing Conference (HPEC). (USA, Waltham, September 9–
, 2014). 6 p.
Колмогоров А. Н., Фомин С. В. Элементы теории функций и функционального анализа. М.: Наука, 1976. 543 с.
Колмогоров А Н., Фомин С. В. Элементы теории функций и функционального анализа. 7-е изд. М.: Физматлит, 2004. 572 с.
Яглом А. М., Яглом И. М. Вероятность и информация. М.: КомКнига, 2007. 512 с.
Hodakov V., Kozel V., Sokolov A. Analysis of Information Technology of the Management System of the Higher Educational Institution. Technology Audit and production reserves. 2017. № 4(2). С. 4−12.
Рожков С. О. Методи і засоби оцінки якості тканин у системах керування текстильним виробництвом: Монографія. Херсон: Олді-Плюс, 2011. 318 с.
Бражник Д. О. Модели и методы повышения устойчивости к возмущениям в системах оптической идентификации: дисс. … канд. техн. наук: 05.13.06. Херсонский национальный технический университет. Херсон, 2012.
Рожков С. А., Бражник Д. А. Использование нейросетевых структур для построения систем распознавания образов. Автоматика. Автоматизация. Электротехнические комплексы и системы, 2004. № 2(14). С.247–253.
Tkach V. A., Kashtalyan P. V., Rozhkov S. A. Monitoring and Control Systems of Modem Intellectual Interfaces. IEEE 4th International Conference Methods and Systems of Navigation and Motion Control (MSNMC). (Kyiv, October 18-20, 2016). P. 237−240. DOI: 10.1109/MSNMC.2016.7783151.
