Problems of identification in information systems
The subject of research is models for constructing image classifiers in the description space as a set of descriptors of key points in the recognition of visual objects in computer vision systems. The goal is to create and study the properties of the image classifier based on the construction of a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
National Technical University "Kharkiv Polytechnic Institute"
2021-02-01
|
| Series: | Сучасні інформаційні системи |
| Subjects: | |
| Online Access: | http://ais.khpi.edu.ua/article/view/226801/226363 |
| _version_ | 1819042087042023424 |
|---|---|
| author | Volodymyr Gorokhovatsky Svitlana Gadetska Oleksii Zhadan Oleksandr Khvostenko |
| author_facet | Volodymyr Gorokhovatsky Svitlana Gadetska Oleksii Zhadan Oleksandr Khvostenko |
| author_sort | Volodymyr Gorokhovatsky |
| collection | DOAJ |
| description | The subject of research is models for constructing image classifiers in the description space as a set of descriptors
of key points in the recognition of visual objects in computer vision systems. The goal is to create and study the properties
of the image classifier based on the construction of an ensemble of distributions for the components of the structural description
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, mathematical
statistics, means of determining relevance for 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 etalon descriptions, by the introduction of logical processing and compression
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 of a concentrated part of the
description data makes it possible to improve its distinction from other descriptions. The use of the median as the center of description
has an advantage over the mean. Conclusions. Scientific novelty is the development of an effective method of image
classification based on the introduction of a system of probability distributions for data components, which contributes to indepth
analysis in the data space and increases in classification effectiveness. 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 importance of 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. |
| first_indexed | 2024-12-21T09:35:18Z |
| format | Article |
| id | doaj.art-d64f4daee4cf4bf186f688d42033b051 |
| institution | Directory Open Access Journal |
| issn | 2522-9052 |
| language | English |
| last_indexed | 2024-12-21T09:35:18Z |
| publishDate | 2021-02-01 |
| publisher | National Technical University "Kharkiv Polytechnic Institute" |
| record_format | Article |
| series | Сучасні інформаційні системи |
| spelling | doaj.art-d64f4daee4cf4bf186f688d42033b0512022-12-21T19:08:39ZengNational Technical University "Kharkiv Polytechnic Institute"Сучасні інформаційні системи2522-90522021-02-015151110.20998/2522-9052.2021.1.01Problems of identification in information systemsVolodymyr Gorokhovatsky0https://orcid.org/0000-0002-7839-6223Svitlana Gadetska1https://orcid.org/0000-0002-9125-2363Oleksii Zhadan2https://orcid.org/0000-0002-3415-8450Oleksandr Khvostenko3https://orcid.org/0000-0002-1272-4634Kharkiv National University of RadioElectronicsKharkiv National Automobile and Road UniversityKharkiv National University of RadioElectronicsKharkiv National University of RadioElectronicsThe subject of research is models for constructing image classifiers in the description space as a set of descriptors of key points in the recognition of visual objects in computer vision systems. The goal is to create and study the properties of the image classifier based on the construction of an ensemble of distributions for the components of the structural description 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, mathematical statistics, means of determining relevance for 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 etalon descriptions, by the introduction of logical processing and compression 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 of a concentrated part of the description data makes it possible to improve its distinction from other descriptions. The use of the median as the center of description has an advantage over the mean. Conclusions. Scientific novelty is the development of an effective method of image classification based on the introduction of a system of probability distributions for data components, which contributes to indepth analysis in the data space and increases in classification effectiveness. 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 importance of 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.http://ais.khpi.edu.ua/article/view/226801/226363computer visionimage classificationkey pointorb detectordescriptordescription centerstatistical distributiondescription relevanceclassification effectiveness |
| spellingShingle | Volodymyr Gorokhovatsky Svitlana Gadetska Oleksii Zhadan Oleksandr Khvostenko Problems of identification in information systems Сучасні інформаційні системи computer vision image classification key point orb detector descriptor description center statistical distribution description relevance classification effectiveness |
| title | Problems of identification in information systems |
| title_full | Problems of identification in information systems |
| title_fullStr | Problems of identification in information systems |
| title_full_unstemmed | Problems of identification in information systems |
| title_short | Problems of identification in information systems |
| title_sort | problems of identification in information systems |
| topic | computer vision image classification key point orb detector descriptor description center statistical distribution description relevance classification effectiveness |
| url | http://ais.khpi.edu.ua/article/view/226801/226363 |
| work_keys_str_mv | AT volodymyrgorokhovatsky problemsofidentificationininformationsystems AT svitlanagadetska problemsofidentificationininformationsystems AT oleksiizhadan problemsofidentificationininformationsystems AT oleksandrkhvostenko problemsofidentificationininformationsystems |