|
This article is cited in 1 scientific paper (total in 1 paper)
IMAGE PROCESSING, PATTERN RECOGNITION
Deep learning application for box-office evaluation of images
V. G. Efremtseva, N. G. Efremtseva, E. P. Teterinb, P. E. Teterinc, V. V. Gantsovskya a Independent researcher
b Kovrov State Technological Academy named after V.A.Degtyarev, Kovrov, Vladimir region, Russia
c National Research Nuclear University "MEPhI", Moscow, Russia
Abstract:
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 hyperparameters of the neural network we achieved a classification accuracy of at least 98%.
Keywords:
deep learning, neural networks, image analysis.
Received: 24.01.2019 Accepted: 11.09.2019
Citation:
V. G. Efremtsev, N. G. Efremtsev, E. P. Teterin, P. E. Teterin, V. V. Gantsovsky, “Deep learning application for box-office evaluation of images”, Computer Optics, 44:1 (2020), 127–132
Linking options:
https://www.mathnet.ru/eng/co770 https://www.mathnet.ru/eng/co/v44/i1/p127
|
Statistics & downloads: |
Abstract page: | 95 | Full-text PDF : | 22 | References: | 17 |
|