Islamic calligraphy is a substantial cultural element in the countries that share Arabic script. Despite its prevalence and importance, Islamic calligraphy has not significantly benefited from modern technologies, and there are considerable gaps between the affordances of digital tools and the subtle requirements of this domain. This project explores the use of Generative Adversarial Networks (GANs) as an option that can fill the gap between digital tools and fundamental aspects of Islamic calligraphy, and as a new tool that can expand the creative space of artists and designers who use Islamic calligraphy in their works. This study also promotes an informed approach toward using GANs with a focus on domain-specific requirements of Islamic calligraphy. Some of the potentials of using GANs in Islamic calligraphy are depicted through analyzing the results of a GAN trained on a custom-made and regularized dataset of nasta’līq script. The results are also used to make calligraphy pieces with a new mode of expression.

• Author