Дослідження результативності класифікаторів зображень за статистичними розподілами для компонентів структурного опису

Гороховатський, В. О.; Гадецька, С. В.; Жадан, О. В.; Хвостенко, О. В.

Публікація:
Дослідження результативності класифікаторів зображень за статистичними розподілами для компонентів структурного опису

dc.contributor.author	Гороховатський, В. О.
dc.contributor.author	Гадецька, С. В.
dc.contributor.author	Жадан, О. В.
dc.contributor.author	Хвостенко, О. В.
dc.date.accessioned	2021-03-19T12:24:55Z
dc.date.available	2021-03-19T12:24:55Z
dc.date.issued	2021
dc.description.abstract	The subjectof research is models for constructing image classifiers in the description space as a set of descriptors of key points in the recognition of visualobjects in computer vision systems. The goalis to create and study the properties of the image classifier basedon the construction of an ensemble of distributions for the components of the structural descrip-tion using various models of classification decisions, which provides effective classification. Tasks: construction of classification models in the synthesized space of images of probability distributions, analysis of parameters influencing their efficiency, experimental evaluation of the effectiveness of classifiers by means of software modeling based on the results of processing the experimental image base. The applied methods are: ORB detector for formation of keypoint descriptors, data mining, mathe-matical statistics, means of determining relevancefor sets of data vectors, software modeling. The obtained results: The developed method of classification confirms its efficiency and effectiveness for image classification. The effectiveness of the method can be enhanced by the introduction of a variety of types of metrics and measures of similarity between centers and descriptors, by the choice of method of forming centers for reference etalondescriptions, by the introduction of logical processing and com-pression of the structural description. The best results of the classification were shown by the model using the most important class by the distribution vector for each descriptor corresponding to the mode parameter. The use ofa concentrated part of the description data makes it possible to improve itsdistinction from other descriptions. The use of the median as the center of de-scription has an advantage over the mean. Conclusions. Scientific novelty isthe development of an effective method of image classification based on the introduction of a systemof probability distributions for data components, which contributes to in-depth analysis in the data space and increases inclassificationeffectiveness. The classifier is implemented in the variants of comparing the integrated representation of distributions by classes and on the basis of mode analysis for the distributions of individual components. The practical importanceof the work is the construction of classification models in the modified data space, confirmation of the efficiency of the proposed modifications of data analysis on examples of images, development of software models for implementation of the proposed classification methods in computer vision systems.	uk_UA
dc.identifier.citation	Дослідження результативності класифікаторів зображень за статистичними розподілами для компонентів структурного опису / В. О. Гороховатський, С. В. Гадецька, О. В. Жадан, О. В. Хвостенко // Сучасні інформаційні системи. – 2021. – Т. 5, №1. – С. 5–11.	uk_UA
dc.identifier.uri	http://openarchive.nure.ua/handle/document/15012
dc.language.iso	uk	uk_UA
dc.subject	комп'ютерний зір	uk_UA
dc.subject	image classification	uk_UA
dc.subject	статистичний розподіл	uk_UA
dc.subject	релевантність описів	uk_UA
dc.title	Дослідження результативності класифікаторів зображень за статистичними розподілами для компонентів структурного опису	uk_UA
dc.title.alternative	Study of the effectiveness of image classifiers by statistical distributions for components of structural description	uk_UA
dc.type	Article	uk_UA
dspace.entity.type	Publication