3. Surveys: The State of the Domain

While, the previous chapter, Preliminaries, meticulously mapped the landscape of AI font generation and consolidated its discovered features into a comprehensive literature database. This chapter, Surveys, transforms that accumulated knowledge into practical insights for both type design and machine learning domains.

The chapter scrutinises the intersection between type design and machine learning domains, addressing three knowledge gap questions:

These questions mark the crossroads where practitioners from both domains can engage in meaningful dialogue despite speaking notably different technical languages.

The investigation unfolds through three distinct surveys, each illuminating a different facet of this interdisciplinary landscape:

The Applications survey examines the various tasks for which AI models are trained, addressing how generative models might serve type design practices. This exploration culminates in precise definitions of AI applications – a necessary translation between the technical capabilities of machine learning and the practical needs of type design.

The Datasets survey catalogues and analyses the common datasets employed in font generation projects, investigating what the field of type design can contribute to machine learning. This examination produces a comprehensive summary of dataset types, their distinctive features, and their current limitations.

The Representations survey delves into the technical presentation of data, exploring how type design information can be effectively communicated to learning algorithms. This investigation clarifies the various approaches to data representation, building a bridge between the visual language of type design and the mathematical abstractions required by machine learning systems.

License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License .

Creative Commons License

Citation

If this work is useful for your research, please cite it as:

@phdthesis{paldia2025generative,
  title={Research and development of generative neural networks for type design},
  author={Paldia, Filip},
  year={2025},
  school={Academy of Fine Arts and Design in Bratislava},
  address={Bratislava, Slovakia},
  type={Doctoral thesis},
  url={https://lttrface.com/doctoral-thesis/},
  note={Department of Visual Communication, Studio Typo}
}