CISUC

Evotype: Evolutionary Type Design

Authors

Abstract

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.

Conference

Colin Johnson and Adrian Carballal and João Correia editors , Proceedings of the 4th International Conference on Evolutionary and Biologically Inspired Music, Sound, Art and Design, EvoMUSART 2015, Copenhagen, Denmark, April 8-10, 2015, April 2015

DOI


Cited by

No citations found