<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>With the development and progress of society, traditional painting creation techniques cannot realize the development needs of modern society for paintings, and it is necessary to constantly innovate and improve the painting creation techniques. Based on the structure of the generative adversarial network, this paper utilizes the one-dimensional midpoint substitution method and dichotomous method to generate the rock outline in painting creation and combines the generative adversarial network to establish the style migration model of modern painting creation techniques and morphological language. Unity was used to construct the validation dataset, and for the style migration of painting creation techniques, we verified it in terms of stroke curvature, FID value, and peak signal-to-noise ratio, and analyzed the evolution of painting creation techniques and morphology language. The results show that the difference in stroke curvature before and after the contour migration of painting creation techniques is 3.27, the peak signal-to-noise ratio reaches 25.43 dB, and the evolution of comprehensive painting in creation techniques is in an upward trend, with an average annual growth rate of 13.07% from 2012 to 2020. Generative adversarial networks can be used in modern painting creation techniques to increase the richness of paintings and establish a spiritual connection between painters and audiences.</p>
</abstract>

With the development and progress of society, traditional painting creation techniques cannot realize the development needs of modern society for paintings, and it is necessary to constantly innovate and improve the painting creation techniques. Based on the structure of the generative adversarial network, this paper utilizes the one-dimensional midpoint substitution method and dichotomous method to generate the rock outline in painting creation and combines the generative adversarial network to establish the style migration model of modern painting creation techniques and morphological language. Unity was used to construct the validation dataset, and for the style migration of painting creation techniques, we verified it in terms of stroke curvature, FID value, and peak signal-to-noise ratio, and analyzed the evolution of painting creation techniques and morphology language. The results show that the difference in stroke curvature before and after the contour migration of painting creation techniques is 3.27, the peak signal-to-noise ratio reaches 25.43 dB, and the evolution of comprehensive painting in creation techniques is in an upward trend, with an average annual growth rate of 13.07% from 2012 to 2020. Generative adversarial networks can be used in modern painting creation techniques to increase the richness of paintings and establish a spiritual connection between painters and audiences.

Analysis of the Technique and Morphological Language of Modern Painting Creation Based on Generative Adversarial Networks

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

With the development and progress of society, traditional painting creation techniques cannot realize the development needs of modern society for paintings,...

Analysis of the Technique and Morphological Language of Modern Painting Creation Based on Generative Adversarial Networks

Online veröffentlicht: 31. Jan. 2024

Seitenbereich: -

Eingereicht: 22. Dez. 2023

Akzeptiert: 27. Dez. 2023

DOI: https://doi.org/10.2478/amns-2024-0279

Schlüsselwörter
Generative adversarial network, One-dimensional midpoint substitution method, Mountain and rock model, Style migration model, Painting creation

© 2024 Liang Zhao, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Analysis of the Technique and Morphological Language of Modern Painting Creation Based on Generative Adversarial Networks

Online veröffentlicht: 31. Jan. 2024

Seitenbereich: -

Eingereicht: 22. Dez. 2023

Akzeptiert: 27. Dez. 2023

DOI: https://doi.org/10.2478/amns-2024-0279

SchlüsselwörterGenerative adversarial network, One-dimensional midpoint substitution method, Mountain and rock model, Style migration model, Painting creation

© 2024 Liang Zhao, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Generative adversarial network, One-dimensional midpoint substitution method, Mountain and rock model, Style migration model, Painting creation