Abstract
The method of this study is to use the Generative Adversarial Network (GAN) to learn the style features of the ten aesthetic principles, and use the generator in the GAN to generate user interface (UI) images of various design styles, and then label them through the classification model. When designers enter style keywords, the system can output related architectural pictures as their reference materials. This system is designed to help designers complete tasks within a limited time while improving design quality. Through machine learning and generative technology, it provides diverse reference materials to stimulate designers’ creativity while ensuring work efficiency.
Presenters
Chen PeilinUI Engineer, Digital Education Institute, Institute for Information Industry, Taipei, Taiwan
Details
Presentation Type
Paper Presentation in a Themed Session
Theme
2024 Special Focus—Cultures of Transformative Design
KEYWORDS
Generative Design;Aesthetic Principles;UI design;Generative Adversarial Network;Inspired Creation
