Публікація:
Image Classification Based on the Kohonen Network and the Data Space Modification

dc.contributor.authorGorokhovatskyi, V.
dc.contributor.authorTvoroshenko, I.
dc.date.accessioned2020-05-21T19:11:17Z
dc.date.available2020-05-21T19:11:17Z
dc.date.issued2020
dc.description.abstractIn this paper, we propose the solution of visual object recognition in computer vision problems using the classification of descriptors of image key points based on the training of Kohonen neural network on the description data of etalons images. According to the results of training within the set of etalons, the image classification method has been improved by defining a specific data space in the form of a statistical center for each etalon. We propose mathematical models for the bitwise analysis of multiple descriptors searching for the centers and the method for convolution of descriptions from multiple descriptors with the determining a posteriori probabilities for the system of bit centers. Methods of data space transformation of description bits are proposed for various options for Kohonen network training, processing and estimation of class centers. The software implementation of the changed classifier was performed as well as the processing time with different options for determining the space of training data was estimated. Experimental researches confirmed the high efficiency of classification preserving sufficient performance and the ability to use proposed methods in real-time applications.uk_UA
dc.identifier.citationGorokhovatskyi V., Tvoroshenko I. (2020) Image Classification Based on the Kohonen Network and the Data Space Modification. In CEUR Workshop Proceedings: Computer Modeling and Intelligent Systems (CMIS-2020). 2608. pp. 1013-1026. Available online: http://ceur-ws.org/Vol-2608/uk_UA
dc.identifier.urihttp://openarchive.nure.ua/handle/document/11781
dc.language.isoenuk_UA
dc.subjectcomputer visionuk_UA
dc.subjectkey pointuk_UA
dc.titleImage Classification Based on the Kohonen Network and the Data Space Modificationuk_UA
dc.typeConference proceedingsuk_UA
dspace.entity.typePublication

Файли

Оригінальний пакет
Зараз показано 1 - 1 з 1
Завантаження...
Зображення мініатюри
Назва:
CMIS2020paper76.pdf
Розмір:
767.52 KB
Формат:
Adobe Portable Document Format
Ліцензійний пакет
Зараз показано 1 - 1 з 1
Немає доступних мініатюр
Назва:
license.txt
Розмір:
9.42 KB
Формат:
Item-specific license agreed upon to submission
Опис: