Title: Application of a deep convolutional neural network in the images colorization problem
Issue Date: May-2019
Publisher: Новая техника
Citation: Bulygin M.V. Application of a deep convolutional neural network in the images colorization problem / Bulygin M.V., Gayanova M.M., Vulfin A.M., Kirillova A.D., Gayanov R.Ch. // Сборник трудов ИТНТ-2019 [Текст]: V междунар. конф. и молодеж. шк. "Информ. технологии и нанотехнологии": 21-24 мая: в 4 т. / Самар. нац.-исслед. ун-т им. С. П. Королева (Самар. ун-т), Ин-т систем. обраб. изобр. РАН-фил. ФНИЦ "Кристаллография и фотоника" РАН; [под ред. В.А. Фурсова]. - Самара: Новая техника, 2019. – Т. 4: Науки о данных. - 2019. - С. 296-307.
Abstract: Object of the research are modern structures and architectures of neural networks for image processing. Goal of the work is improving the existing image processing algorithms based on the extraction and compression of features using neural networks using the colorization of black and white images as an example. The subject of the work is the algorithms of neural network image processing using heterogeneous convolutional networks in the colorization problem. The analysis of image processing algorithms with the help of neural networks is carried out, the structure of the neural network processing system for image colorization is developed, colorization algorithms are developed and implemented. To analyze the proposed algorithms, a computational experiment was conducted and conclusions were drawn about the advantages and disadvantages of each of the algorithms.
URI: http://repo.ssau.ru/jspui/handle/123456789/11165
Appears in Collections:Информационные технологии и нанотехнологии

Files in This Item:
File Description SizeFormat 
paper38.pdfОсновная статья435.46 kBAdobe PDFView/Open


Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.