Open AccessClassification of surface water objects in visible spectrum images
Author(s) -
Artem Artemev,
Е. А. Казачков,
C. Н. Матюгин,
В. В. Шаронов
Publication year - 2020
Publication title -
vestnik koncerna vko «almaz - antej»
Language(s) - English
Resource type - Journals
ISSN - 2542-0542
DOI - 10.38013/2542-0542-2020-1-87-95
Subject(s) - convolutional neural network , artificial intelligence , surface (topology) , pattern recognition (psychology) , computer science , artificial neural network , spectrum (functional analysis) , visible spectrum , selection (genetic algorithm) , computer vision , mathematics , geometry , optics , physics , quantum mechanics
This paper considers the problem of classifying surface water objects, e.g. ships of different classes, in visible spectrum images using convolutional neural networks. A technique for forming a database of images of surface water objects and a special training dataset for creating a classification are presented. A method for forming and training of a convolutional neural network is described. The dependence of the probability of correct recognition on the number and variants of the selection of specific classes of surface water objects is analysed. The results of recognizing different sets of classes are presented.