Quantitative Research and Modern Transformation of Aesthetic Characteristics of Song-Yuan Landscape Paintings from the Perspective of Big Data Analysis
DOI:
https://doi.org/10.70917/ijcisim-2025-0204Keywords:
landscape painting; image elements; Fourier; modern transformationAbstract
Song Dynasty water painting is the essence of traditional Chinese landscape painting, which has reached unprecedented heights in the development history of landscape painting with its unique aesthetic interest and highly matured brush and ink techniques. In this paper, from the perspective of big data analysis, we quantitatively study the divine aesthetic characteristics of Song and Yuan landscape paintings as well as explore their modern transformation. Firstly, we pre-processed the landscape paintings by image processing methods, extracted the low-level features, high-level features and regional features by using aesthetic feature extraction methods (HSV color model, Fourier description, Circular LBP), and established an aesthetic score assessment model. After quantitative experimental analysis of the aesthetic features of landscape paintings, the mean value of the area proportion of each image element in Song-Yuan landscape paintings is obtained, in which mountains, tall plants, and the sky account for a relatively high percentage, which is 31.28%, 20.36%, and 16.15%, respectively, and secondly, the stylistic changes of Song-Yuan landscape paintings are complex and diverse. Finally, the modern transformation method of Song Yuan landscape painting and its application in jewelry design are explored and analyzed by using perceptual evaluation method, and the results show that the Alpha reliability coefficient is 0.813, which is more than 0.6, and the factors and dimensions of the perceptual imagery evaluation system are established with high reliability. The research enhances the cognition of aesthetic characteristics of Song and Yuan landscape paintings as well as provides a new path in modern inheritance.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Manni Li

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