15. February 2021 : How deep neural networks and style transfer help to understand the development of artistic styles:
Clay V, Schrumpf J, Tessenow Y, Leder H, Ansorge U and König P (2020).
A quantitative analysis of the taxonomy of artistic styles.
DOI: https://doi.org/10.16910/jemr.13.2.5. J Eye Mov Res 13:2
Classifying artists and their work as distinct art styles has been an important, yet controversy-prone task of scholars in the field of art history.
Our project investigated differences in aesthetic qualities of seven art styles with state-of-the-art deep-learning methods. We conducted an eye-tracking study as well as a visual singelton search study to measure the behavior of subjects when viewing new art images. The experiments demonstrate differences in behavior when viewing images of varying art styles, allowing us to derive and construct respective hierarchical clusterings.
Our study reveals a novel perspective on the classification of artworks into stylistic eras and motivates future research in the domain of empirical aesthetics through quantitative means.