Spectral analysis of images

[Eugene Lutsenko]

Thanks to Your help I could do this:

UDC 004.8
Engineering

AUTOMATED SYSTEM-COGNITIVE ANALYSIS OF SPECIFIC SPECTRAL AND INTEGRATED IMAGES IN "EIDOS" SYSTEM (APPLICATION OF INFORMATION THEORY AND COGNITIVE TECHNOLOGIES IN SPECTRAL ANALYSIS)

Lutsenko Eugeny Veniaminovich
Dr.Sci.Econ., Cand.Tech.Sci., professor
Scopus Author ID: 57191193316
RSCI SPIN-code: 9523-7101
prof.lutsenko@gmail.com
Kuban State Agrarian University, Krasnodar, Russia

Automated system-cognitive analysis (ASC-analysis) for images provides automatic identification of specific characteristics of the given images from the color of the pixels and image edges, the synthesis of generalized images of pictures (classes), identifying the most and the least specific image features for the class, determining values of features of images for their differentiation, deletion low-value characteristics (abstraction) from the model, problem solving for quantitative comparison of specific images with generalized images of classes and generalized images of the classes with each other, and objectives of the study of the simulated subject area by studying its model. The work discusses the new features of the ASC-analysis and its implementing intellectual system called "Eidos" for identifying features of images using their spectral analysis, formation of the generalized spectra of classes, the task of comparison of images of specific objects to classes and classes with each other in their spectra. For the first time, it became possible to form the generalized spectra of classes with weights of the colors according to their degree of specificity and unspecific features for classes, and it is not the intensity of the color in the spectrum, but the amount of information in the color on the linking the object with that color to the class. In fact, there is a question of generalization of spectral analysis by using intelligent cognitive technologies and information theory in the spectral analysis. First, everyone is talking about the fact that spectral lines contain information about which element or substance is included in the object, but no one bothered to count what exactly the amount of information is and then use it to determine the composition of the object pattern recognition methods based on the use of this information. Second, spectral analysis is traditionally used to determine the elemental and molecular composition of the object; we propose to use it not only for that, but also to identify any images. A numerical example has been given

Keywords: ASC-ANALYSIS, AUTOMATED SYSTEM-COGNITIVE SPECTRUM ANALYSIS, SPECIFIC GENERALIZED IMAGE, "EIDOS", INFORMATION THEORY, COGNITIVE TECHNOLOGIES

Луценко Е.В. Автоматизированный системно-когнитивный спектральный анализ конкретных и обобщенных изображений в системе "Эйдос" (применение теории информации и когнитивных технологий в спектральном анализе) / Е.В. Луценко // Политематический сетевой электронный научный журнал Кубанского государственного аграрного университета (Научный журнал КубГАУ) [Электронный ресурс]. – Краснодар: КубГАУ, 2017. – №04(128). С. 1 – 64. – IDA [article ID]: 1281704001. – Режим доступа: http://ej.kubagro.ru/2017/04/pdf/01.pdf, 4 у.п.л.

Thank you!!!