Applied Mathematics and Nonlinear Sciences
Journal license

Journal

Applied Mathematics and Nonlinear Sciences


Volume
& Issue

Volume 6, Issue 2


Published
on

November 10, 2022


Pages

1129-1142


DOI

Article

Computational research on flat image design and style based on perceptual feature quantification

Check for updates


Authors

Wei Wang Affiliation:
Hubei Institute of Fine Arts, Wuhan, 430205, China
and Jingli Zheng Affiliation:
Huazhong University of Science and Technology, Wuhan, 430074, China


Abstract

In order to solve the problem that a large number of low-value and easy-to-consume graphic designs consume the human and financial resources of the society and also waste the inherent value of design resources, by dividing the layers of pixels, elements, relations, planes and applications, this article defines the corresponding feature representations and studies related methods for quantifying geometric features, perceptual features and style features. The content includes the extraction method of element colour, the calculation method of layout-aware feature and colour-match-aware feature, and the pairwise comparison method of style feature. The experimental results show that the method proposed in this article has lower complexity and is significantly better than other algorithms. Comparing the method proposed in this article with other methods, the average time of this algorithm is 2.6 s under the condition of guaranteed images. The study of the design feature-driven graphic image style calculation method is not only of great significance for solving repeated design problems but also provides a basis and reference for the future development of intelligent design.


Keywords

graphic design, design features, visual saliency, feature extraction


Citation

Wang, W. & Zheng, J. (2021). Computational research on flat image design and style based on perceptual feature quantification. Applied Mathematics and Nonlinear Sciences, 6(2), 1129–1142. https://doi.org/10.2478/amns.2021.2.00239

Published by: Engineering Journals

Engineering Journals Logo