Evotype: Evolutionary Type Design
An evolutionary generative system for type design, Evotype, is described. The system uses a Genetic Algorithm to evolve a set of individuals composed of line segments, each encoding the shape of a specific character, i.e. a glyph. To simultaneously evolve glyphs for the entire alphabet, an island model is adopted. To assign fitness we resort to a scheme based on Optical Character Recognition. We study the evolvability of the proposed approach as well as the impact of the migration in the evolutionary process. The migration mechanism is explored through three experimental setups: fitness guided migration, random migration, and no migration. We analyse the experimental results in terms of fitness, migration paths, and appearance of the glyphs. The results show the ability of the system to find suitable glyphs and the impact of the migration strategy in the evolutionary process.
KeywordsType design Evolutionary design Island model
This research is partially funded by: iCIS project (CENTRO-07-ST24-FEDER-002003), which is co-financed by QREN, in the scope of the Mais Centro Program and European Union’s FEDER; Fundação para a Ciência e Tecnologia (FCT), Portugal, under the grants SFRH/BD/90968/2012 and SFRH/BD/105506/2014; project ConCreTe. The project ConCreTe acknowledges the financial support of the Future and Emerging Technologies (FET) programme within the Seventh Framework Programme for Research of the European Commission, under FET grant number 611733.
- 1.Butterfield, I., Lewis, M.: Evolving fonts (2000). Consulted in http://accad.osu.edu/~mlewis/AED/Fonts/, October 2014
- 2.Lund, A.: Evolving the shape of things to come: A comparison of direct manipulation and interactive evolutionary design. In: International Conference on Generative Art. Domus Argenia, Rome, Italy (2000)Google Scholar
- 3.Unemi, T., Soda, M.: An iec-based support system for font design. In: Proceedings of the IEEE International Conference on Systems, Man & Cybernetics, Washington, D.C., USA, 5–8 October, pp. 968–973 (2003)Google Scholar
- 4.Schmitz, M.: Genotyp, an experiment about genetic typography. Presented at Generative Art Conference 2004 (2004)Google Scholar
- 5.Levin, G., Feinberg, J., Curtis, C.: The alphabet synthesis machine (2006). Consulted in http://www.alphabetsynthesis.com, October 2014
- 6.Holland, J.H.: Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor (1975)Google Scholar
- 8.Machado, P., Romero, J., Manaris, B.: Experiments in computational aesthetics: An iterative approach to stylistic change in evolutionary art. In: Romero, J., Machado, P. (eds.) The Art of Artificial Evolution: A Handbook on Evolutionary Art and Music, pp. 381–415. Springer, Berlin Heidelberg (2007)Google Scholar
- 10.Artan, Y., Burry, A., Kozitsky, V., Paul, P.: Efficient smqt features for snow-based classification on face detection and character recognition tasks. In: 2012 Western New York Image Processing Workshop (WNYIPW), pp. 45–48, Nov 2012Google Scholar
- 11.Carlson, A., Cumby, C., Rosen, J., Roth, D.: The snow learning architecture. Technical report UIUCDCS-R-99-2101, UIUC Computer Science Department, May 1999Google Scholar