Skip to main content
SpringerLink
Log in

Using Autoencoders to Generate Skeleton-Based Typography

  • Conference paper
  • First Online:
Artificial Intelligence in Music, Sound, Art and Design (EvoMUSART 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13988))

  • 1286 Accesses

Abstract

Type Design is a domain that multiple times has profited from the emergence of new tools and technologies. The transformation of type from physical to digital, the dissemination of font design software and the adoption of web typography make type design better known and more accessible. This domain has received an even greater push with the increasing adoption of generative tools to create more diverse and experimental fonts. Nowadays, with the application of Machine Learning to various domains, typography has also been influenced by it. In this work, we produce a dataset by extracting letter skeletons from a collection of existing fonts. Then we trained a Variational Autoencoder and a Sketch Decoder to learn to create these skeletons that can be used to generate new ones by exploring the latent space. This process also allows us to control the style of the resulting skeletons and interpolate between different characters. Finally, we developed new glyphs by filling the generated skeletons based on the original letters’ stroke width and showing some applications of the results.

J. Parente and L. Gonçalo—These authors contributed equally to this work.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 69.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 89.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    <https://github.com/tiagofmartins/skelefont>.

  2. 2.

    An example video containing multiple skeleton interpolations can be seen at https://imgur.com/a/qf1m2Da.

  3. 3.

    A video showing multiple skeleton and stroke width interpolations can be seen at https://imgur.com/3XTecg5.

References

  1. Azadi, S., Fisher, M., Kim, V.G., Wang, Z., Shechtman, E., Darrell, T.: Multi-Content GAN for Few-Shot Font Style Transfer. CoRR, abs/1712.00516 (2017)

    Google Scholar 

  2. Balashova, E., Bermano, A.H., Kim, V.G., DiVerdi, S., Hertzmann, A., Funkhouser, T.A.: Learning a stroke-based representation for fonts. Comput. Graph. Forum 38(1), 429–442 (2019)

    Google Scholar 

  3. Campbell, N.D.F., Kautz, J.: Learning a manifold of fonts. ACM Trans. Graph. 33(4), Jul 2014. ISSN 0730–0301. https://doi.org/10.1145/2601097.2601212

  4. Cheng, K.: Designing type. Yale University Press (2020)

    Google Scholar 

  5. Cunha, J.M., Martins, T., Martins, P., Bicker, J., Machado, P.: Typeadviser: a type design aiding-tool. In: C3GI@ ESSLLI (2016)

    Google Scholar 

  6. Google. Google Web Fonts (2012). http://www.google.com/webfonts/v2/. visited 2022-01-02

  7. Ha, D., Eck, D.: A neural representation of sketch drawings. In: ICLR (2018). https://openreview.net/forum?id=Hy6GHpkCW

  8. Ho, K.: Organizing the World of Fonts with AI (2017). https://medium.com/ideo-stories/organizing-the-world-of-fonts-with-ai-7d9e49ff2b25, visited 03/01/2022

  9. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)

    Article  Google Scholar 

  10. Hong, S.: Font-VAE (2019). https://github.com/hngskj/Font-VAE, visited 2022-01-02

  11. Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14–16, 2014, Conference Track Proceedings (2014)

    Google Scholar 

  12. Kullback, S., Leibler, R.A.: On information and sufficiency. Ann. Math. Statist. 22(1), 79–86 (1951)

    Article  MathSciNet  MATH  Google Scholar 

  13. Li, T.-M., Lukáč, M., Gharbi, M., Ragan-Kelley, J.: Differentiable vector graphics rasterization for editing and learning. ACM Trans. Graph. (TOG) 39(6), 1–15 (2020)

    Article  Google Scholar 

  14. Lopes, R.G., Ha, D., Eck, D., Shlens, J.: A learned representation for scalable vector graphics. In: DGS@ICLR. OpenReview.net (2019)

    Google Scholar 

  15. Martins, T., Correia, J., Costa, E., Machado, P.: Evotype: evolutionary type design. In: Johnson, C., Carballal, A., Correia, J. (eds.) EvoMUSART 2015. LNCS, vol. 9027, pp. 136–147. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-16498-4_13

    Chapter  Google Scholar 

  16. Martins, T., Parente, J., Bicker, J.: Skelefont (2018). https://github.com/tiagofmartins/skelefont, visited 2022-02-01

  17. Martins, T., Cunha, J.M., Bicker, J., Machado, P.: Dynamic visual identities: from a survey of the state-of-the-art to a model of features and mechanisms. Visible Lang. 53(2) (2019)

    Google Scholar 

  18. McCormack, J.P., Dorin, A., Christopher, T.: Innocent. Generative design: a paradigm for design research. In: Redmond, J., Durling, D., de Bono, A. (eds.) Futureground, vol. 2, Monash University, 2005. ISBN 0975606050

    Google Scholar 

  19. Phan, Q.H., Fu, H., Chan, A.B.: FlexyFont: learning transferring rules for flexible typeface synthesis. Comput. Graph. Forum 34(7), 245–256 (2015)

    Google Scholar 

  20. Qiao, J.: Fontjoy - Generate font pairings in one click. http://fontjoy.com/, visited 2022-01-02

  21. Rehling, J., Hofstadter, D.: Letter spirit: a model of visual creativity. In: ICCM, pp. 249–254 (2004)

    Google Scholar 

  22. Schmitz, M.: genoTyp, an experiment about genetic typography. In: Proceedings of Generative Art 2004 (2004)

    Google Scholar 

  23. Semeniuta, S., Severyn, A., Barth, E.: Recurrent dropout without memory loss. In: Calzolari, N., Matsumoto, Y., Prasad, R. (eds.) COLING, pp. 1757–1766. ACL (2016). ISBN 978-4-87974-702-0

    Google Scholar 

  24. Shamir, A., Rappoport, A.: Feature-based design of fonts using constraints. In: Hersch, R.D., André, J., Brown, H. (eds.) EP/RIDT -1998. LNCS, vol. 1375, pp. 93–108. Springer, Heidelberg (1998). https://doi.org/10.1007/BFb0053265

    Chapter  Google Scholar 

  25. Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  26. Suveeranont, R., Igarashi, T.: Example-based automatic font generation. In: Taylor, R., Boulanger, P., Krüger, A., Olivier, P. (eds.) SG 2010. LNCS, vol. 6133, pp. 127–138. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-13544-6_12

    Chapter  Google Scholar 

  27. van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)

    MATH  Google Scholar 

  28. Willen, B., Strals, N.: Lettering & type: creating letters and designing typefaces. Princeton Architectural Press (2009)

    Google Scholar 

  29. Zhang, T.Y., Suen, C.Y.: A fast parallel algorithm for thinning digital patterns. Commun. ACM 27(3), 236–239 (1984)

    Google Scholar 

Download references

Acknowledgments

This work is partially funded by national funds through the FCT - Foundation for Science and Technology, I.P., within the scope of the project CISUC - UID/CEC/00326/2020 and by European Social Fund, through the Regional Operational Program Centro 2020, and under the grant SFRH/BD/148706/2019.

Author information

Authors and Affiliations

  1. CISUC, Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal

    Jéssica Parente, Luís Gonçalo, Tiago Martins, João Miguel Cunha, João Bicker & Penousal Machado

Authors
  1. Jéssica Parente
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Luís Gonçalo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tiago Martins
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. João Miguel Cunha
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. João Bicker
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Penousal Machado
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Jéssica Parente or Luís Gonçalo .

Editor information

Editors and Affiliations

  1. University of Nottingham, Nottingham, UK

    Colin Johnson

  2. University of A Coruña, A Coruña, Spain

    Nereida Rodríguez-Fernández

  3. University of Coimbra, Coimbra, Portugal

    Sérgio M. Rebelo

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Parente, J., Gonçalo, L., Martins, T., Cunha, J.M., Bicker, J., Machado, P. (2023). Using Autoencoders to Generate Skeleton-Based Typography. In: Johnson, C., Rodríguez-Fernández, N., Rebelo, S.M. (eds) Artificial Intelligence in Music, Sound, Art and Design. EvoMUSART 2023. Lecture Notes in Computer Science, vol 13988. Springer, Cham. https://doi.org/10.1007/978-3-031-29956-8_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-29956-8_15

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-29955-1

  • Online ISBN: 978-3-031-29956-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation