Research on the Style of Art Works based on Deep Learning

In view of the unsatisfactory effect and major limitations of the style transfer of art works, this paper takes Chinese ink painting for the research subject. The obvious texture characteristics of Chinese ink painting are selected as the input of the Cycle Generative Adversarial Network (CycleGAN)...

Full description

Saved in:
Bibliographic Details
Main Author: Shulin Liu
Format: Article
Language:English
Published: Wiley 2022-01-01
Series:Journal of Advanced Transportation
Online Access:http://dx.doi.org/10.1155/2022/5433623
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849693426491064320
author Shulin Liu
author_facet Shulin Liu
author_sort Shulin Liu
collection DOAJ
description In view of the unsatisfactory effect and major limitations of the style transfer of art works, this paper takes Chinese ink painting for the research subject. The obvious texture characteristics of Chinese ink painting are selected as the input of the Cycle Generative Adversarial Network (CycleGAN) model builder, and the relativistic evaluator is employed to improve the model loss function and the adversarial loss function. An improved art style transfer method of the CycleGAN model is proposed. The experiment shows that the improved CycleGAN model is efficient and feasible for style transfer. Compared with the traditional CycleGAN model, the proposed model performs better in GAN train and GAN test, with a higher average pass rate, which is an increase of nearly 10%. At the same time, with the increase of the number of iterations, the training time of the improved model is close to that of the original model, but the image of the improved model training is larger, which shows that it has more advantages.
format Article
id doaj-art-2c820d1924b44f40ab2d2fe84d112477
institution DOAJ
issn 2042-3195
language English
publishDate 2022-01-01
publisher Wiley
record_format Article
series Journal of Advanced Transportation
spelling doaj-art-2c820d1924b44f40ab2d2fe84d1124772025-08-20T03:20:25ZengWileyJournal of Advanced Transportation2042-31952022-01-01202210.1155/2022/5433623Research on the Style of Art Works based on Deep LearningShulin Liu0Department of Fine ArtsIn view of the unsatisfactory effect and major limitations of the style transfer of art works, this paper takes Chinese ink painting for the research subject. The obvious texture characteristics of Chinese ink painting are selected as the input of the Cycle Generative Adversarial Network (CycleGAN) model builder, and the relativistic evaluator is employed to improve the model loss function and the adversarial loss function. An improved art style transfer method of the CycleGAN model is proposed. The experiment shows that the improved CycleGAN model is efficient and feasible for style transfer. Compared with the traditional CycleGAN model, the proposed model performs better in GAN train and GAN test, with a higher average pass rate, which is an increase of nearly 10%. At the same time, with the increase of the number of iterations, the training time of the improved model is close to that of the original model, but the image of the improved model training is larger, which shows that it has more advantages.http://dx.doi.org/10.1155/2022/5433623
spellingShingle Shulin Liu
Research on the Style of Art Works based on Deep Learning
Journal of Advanced Transportation
title Research on the Style of Art Works based on Deep Learning
title_full Research on the Style of Art Works based on Deep Learning
title_fullStr Research on the Style of Art Works based on Deep Learning
title_full_unstemmed Research on the Style of Art Works based on Deep Learning
title_short Research on the Style of Art Works based on Deep Learning
title_sort research on the style of art works based on deep learning
url http://dx.doi.org/10.1155/2022/5433623
work_keys_str_mv AT shulinliu researchonthestyleofartworksbasedondeeplearning