Background Artificial intelligence had been rapidly expanding its application areas and the design discipline is not an exception. While the majority of previous design studies viewed artificial intelligence from the macroscopic or abstract point of view, few studies have investigated its implication in terms of practical applications. This study intends to understand and predict the impact that artificial intelligence will have on the graphic design field by focusing on GAN (Generative Adversarial Network) of deep learning models. Methods We looked closely at review papers registered in AI journals, and selected applications related to graphic design elements included in the research scope. Especially, typography (font), layout, color and logos were searched by combining them with GAN. We also focused on design applications rather than mathematical models. By analyzing the core concepts and characteristics of each GAN model, implications for how it can be utilized in the future graphic design process, were derived. Results Since the GAN program has the characteristics of generation, mix generation, intelligence, imitativeness and automation, it will bring source expansion, promotion of inspiration and increase of convenience to graphic designers. This effect can be used as a useful communication tool for conversations with clients in the graphic design process, and can promote inspiration and increase convenience even at the stage of proposing ideas or establishing plans. In addition, GAN is an interactive tool that is composed of intelligence. Especially, idea creation will bring more excellent effects than existing design programs. Conclusions The GAN program will not only enhance the current graphic design tasks, but also bring changes to idea generation, the scope of expression, and even the role itself. However, its data-based nature may restrict itself from coming up with a truly novel idea. We have a limited understanding of the program’s capacity and potential and need to carefully monitor its future progress.
|Journal||Archives of Design Research|
|Publication status||Published - 2022|
Bibliographical notePublisher Copyright:
© This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/), which permits unrestricted educational and non-commercial use, provided the original work is properly cited.
All Science Journal Classification (ASJC) codes
- Visual Arts and Performing Arts
- Computer Graphics and Computer-Aided Design