1.2. Objectives: The Purpose of the Project

The objectives, research questions, and methodology of this thesis are structured across three chapters, each addressing distinct aspects of AI font generation research.

The Preliminaries chapter establishes foundational understanding. Its objectives focus on mapping the AI font generation domain in its current state and trajectory. The research question asks: “How does the landscape of AI font generation appear, and in what ways is it evolving?” The methodological approach employs an explorative methodology, drawing inspiration from Grounded Theory principles to systematically analyse and categorise the field’s components.

The Surveys chapter delves deeper into practical challenges. Its objectives concentrate on understanding the problems and obstacles that hinder AI font generation adoption. The research question investigates: “What are the particular obstacles preventing AI font generation from achieving sufficient quality for practical type design implementation?” The methodology synthesises findings from an extensive literature database and analytical memos developed during the chapter of Preliminaries, providing a comprehensive assessment of current limitations.

The Project chapter transitions from analysis to implementation. Its objectives centre on delivering a tangible artefact with demonstrable value to the field. The research explores: “Can regularising real type design data meaningfully improve the quality of AI font generation?” The methodology combines skeleton type design principles for dataset construction with empirical evaluation through comparison studies, employing predefined heuristics to assess outcomes.

Each chapter’s objectives, research questions, and methodology are further elaborated within their respective sections, where the theoretical frameworks and practical approaches are examined in greater detail. This structure progresses from foundational understanding through analytical insight to practical implementation, reflecting the journey from theoretical exploration to tangible contribution.

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}
}