Emotion-Inspired Painterly Rendering

Jung-Hyun Lee

doi:10.1109/ACCESS.2020.2999460

2020-01-01

Jung-Hyun Lee

Jong‐In Choi

Sanghyun Seo *

DOI：10.1109/ACCESS.2020.2999460

原文链接

查看原文

摘要

En 中文

When painters draw, they do not draw what they see; they reflect their emotions through specific forms of artistic expression. Through this empathy, humans derive aesthetic satisfaction. Psychological studies on art and emotions have been extensively conducted since the 20th century, and it has been found that artistic activities such as painting and writing have a positive effect on human emotions. However, it is difficult for a non-professional painter to express human emotions in a picture using artistic elements. The aim of this study was to propose a user emotion-inspired painterly rendering process to help non-professionals reflect their emotions through painting. To accomplish this aim, a painter-rendering system that automatically creates digital paintings with parameterized painting features was used. We analyzed the correlation between human emotions and the rendering parameters affecting the painting style through a user study, and we estimated the rendering parameter values for specific emotions. The results showed that colors and emotions were closely linked, and color scheme was an influential factor in the paintings. Furthermore, we developed a recoloring algorithm based on Kobayashi's three color systems classified as human emotions, and we created paintings that better reflect specific emotions. The proposed algorithm was validated through a user satisfaction survey. Hence, the proposed system can improve a user's understanding of painting and create paintings that reflect specific emotions.

Keyword:

Affective computing

emotion analysis

image stylization

painterly rendering

recoloring