An Empirical Study on the Artificial Intelligence-Aided Quantitative Design of Art Images

This paper presents an indepth analysis and research on the quantitative design of fine art images through artificial intelligence algorithms. A CycleGAN-based network model for automatic generation of sketches of fine art images is constructed to extract the edge and contour features of fine art im...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Wen Zhang, Sang-Bing Tsai
Formato: article
Lenguaje:EN
Publicado: Hindawi-Wiley 2021
Materias:
T
Acceso en línea:https://doaj.org/article/4a1e872870044b34a1b3e84146d74a9e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:4a1e872870044b34a1b3e84146d74a9e
record_format dspace
spelling oai:doaj.org-article:4a1e872870044b34a1b3e84146d74a9e2021-11-08T02:36:35ZAn Empirical Study on the Artificial Intelligence-Aided Quantitative Design of Art Images1530-867710.1155/2021/8036323https://doaj.org/article/4a1e872870044b34a1b3e84146d74a9e2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/8036323https://doaj.org/toc/1530-8677This paper presents an indepth analysis and research on the quantitative design of fine art images through artificial intelligence algorithms. A CycleGAN-based network model for automatic generation of sketches of fine art images is constructed to extract the edge and contour features of fine art images. The network uses 512×1024 high-resolution art images as input and Pitchman as a discriminator. To further enhance the sketch generation effect, a bilateral filtering algorithm is added to the generator model for noise reduction, and then a K-means algorithm is used for color quantization to solve the problem of cluttered lines in the generated sketches. The experimental results show that the network model can effectively realize the automatic generation of art image sketches and can retain the detailed part of the costume information well. A rendering platform is built to realize the application of art image generation algorithms and coloring algorithms. The platform integrates the functions of image preprocessing, sketch generation, and sketch coloring, demonstrates the results of the main research content of this paper, and finally increases the interest of the system through the rendering function of the art image grid, which further improves the practicality of the platform.Wen ZhangSang-Bing TsaiHindawi-WileyarticleTechnologyTTelecommunicationTK5101-6720ENWireless Communications and Mobile Computing, Vol 2021 (2021)
institution DOAJ
collection DOAJ
language EN
topic Technology
T
Telecommunication
TK5101-6720
spellingShingle Technology
T
Telecommunication
TK5101-6720
Wen Zhang
Sang-Bing Tsai
An Empirical Study on the Artificial Intelligence-Aided Quantitative Design of Art Images
description This paper presents an indepth analysis and research on the quantitative design of fine art images through artificial intelligence algorithms. A CycleGAN-based network model for automatic generation of sketches of fine art images is constructed to extract the edge and contour features of fine art images. The network uses 512×1024 high-resolution art images as input and Pitchman as a discriminator. To further enhance the sketch generation effect, a bilateral filtering algorithm is added to the generator model for noise reduction, and then a K-means algorithm is used for color quantization to solve the problem of cluttered lines in the generated sketches. The experimental results show that the network model can effectively realize the automatic generation of art image sketches and can retain the detailed part of the costume information well. A rendering platform is built to realize the application of art image generation algorithms and coloring algorithms. The platform integrates the functions of image preprocessing, sketch generation, and sketch coloring, demonstrates the results of the main research content of this paper, and finally increases the interest of the system through the rendering function of the art image grid, which further improves the practicality of the platform.
format article
author Wen Zhang
Sang-Bing Tsai
author_facet Wen Zhang
Sang-Bing Tsai
author_sort Wen Zhang
title An Empirical Study on the Artificial Intelligence-Aided Quantitative Design of Art Images
title_short An Empirical Study on the Artificial Intelligence-Aided Quantitative Design of Art Images
title_full An Empirical Study on the Artificial Intelligence-Aided Quantitative Design of Art Images
title_fullStr An Empirical Study on the Artificial Intelligence-Aided Quantitative Design of Art Images
title_full_unstemmed An Empirical Study on the Artificial Intelligence-Aided Quantitative Design of Art Images
title_sort empirical study on the artificial intelligence-aided quantitative design of art images
publisher Hindawi-Wiley
publishDate 2021
url https://doaj.org/article/4a1e872870044b34a1b3e84146d74a9e
work_keys_str_mv AT wenzhang anempiricalstudyontheartificialintelligenceaidedquantitativedesignofartimages
AT sangbingtsai anempiricalstudyontheartificialintelligenceaidedquantitativedesignofartimages
AT wenzhang empiricalstudyontheartificialintelligenceaidedquantitativedesignofartimages
AT sangbingtsai empiricalstudyontheartificialintelligenceaidedquantitativedesignofartimages
_version_ 1718443090737364992