Publication: Deep learning application for box-office evaluation of images
Дата
2020
Авторы
Efremtsev, V. G.
Efremtsev, N. G.
Teterin, E. P.
Gantsovsky, V. V.
Teterin, P. E.
Journal Title
Journal ISSN
Volume Title
Издатель
Аннотация
© 2020, Institution of Russian Academy of Sciences. All rights reserved.The possibility of application a convolutional neural network to assess the box-office effect of digital images is reviewed. We studied various conditions for sample preparation, optimizer algorithms, the number of pixels in the samples, the size of the training sample, color schemes, compression quality, and other photometric parameters in view of effect on training the neural network. Due to the proposed preliminary data preparation, the optimum of the architecture and hy-perparameters of the neural network we achieved a classification accuracy of at least 98%.
Описание
Ключевые слова
Цитирование
Deep learning application for box-office evaluation of images / Efremtsev, V.G. [et al.] // Computer Optics. - 2020. - 44. - № 1. - P. 127-132. - 10.18287/2412-6179-CO-515
URI
https://www.doi.org/10.18287/2412-6179-CO-515
https://www.scopus.com/record/display.uri?eid=2-s2.0-85082048185&origin=resultslist
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS_CPL&DestLinkType=FullRecord&UT=WOS:000520038900016
https://openrepository.mephi.ru/handle/123456789/20444
https://www.scopus.com/record/display.uri?eid=2-s2.0-85082048185&origin=resultslist
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS_CPL&DestLinkType=FullRecord&UT=WOS:000520038900016
https://openrepository.mephi.ru/handle/123456789/20444