4.5. Evaluation

The evaluation phase sought to address questions about the factors impacting the effort and quality.

  1. Dataset size: How does dataset size influence the training length and quality of generated fonts?
  2. Dataset diversity: How does dataset diversity influence the quality of generated fonts?
  3. Training effort: How does the training effort influence the model’s capability to generate fonts?
  4. Fine-tuning efficiency: How does the introduction of a new dataset influence the model’s capability to generate fonts?
  5. Style matching: How accurately does each model match the style of the reference glyphs?
  6. Generation effort: How many generation trials are required to produce the optimal output for font completion?

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}
}