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

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.