Evolving Art Using Multiple Aesthetic Measures

den Heijer E., Eiben A. E.

Conference on EvoApplications 2011: EvoCOMPLEX, EvoGAMES, EvoIASP, EvoINTELLIGENCE, EvoNUM, AND EvoSTOC, Torino, Italy, 27 - 29 April 2011, vol.6625, pp.234-236 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 6625
  • City: Torino
  • Country: Italy
  • Page Numbers: pp.234-236
  • Istanbul Technical University Affiliated: No


In this paper we investigate the applicability of Multi-Objective Optimization (MOO) in Evolutionary Art. We evolve images using an unsupervised evolutionary algorithm and we use two aesthetic measures as fitness functions concurrently. We use three different pairs from a set of three aesthetic measures and we compare the output of each pair to the output of other pairs, and to the output of experiments with a single aesthetic measure (non-MOO). We investigate 1) whether properties of aesthetic measures can be combined using MOO and 2) whether the use of MOO in evolutionary art results in different images, or perhaps "better" images. All images in this paper can be viewed in colour at http://www.few.vu.nl/(similar to)eelco/