Evolutionary Image Synthesis Using a Model of Aesthetics

Created by W.Langdon from gp-bibliography.bib Revision:1.4216

  author =       "Brian J. Ross and William Ralph and Hai Zong",
  title =        "Evolutionary Image Synthesis Using a Model of
  booktitle =    "Proceedings of the 2006 IEEE Congress on Evolutionary
  year =         "2006",
  editor =       "Gary G. Yen and Lipo Wang and Piero Bonissone and 
                 Simon M. Lucas",
  pages =        "3832--3839",
  address =      "Vancouver",
  month =        "6-21 " # jul,
  publisher =    "IEEE Press",
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "0-7803-9487-9",
  URL =          "http://www.cosc.brocku.ca/~bross/research/CEC2006.pdf",
  DOI =          "doi:10.1109/CEC.2006.1688430",
  size =         "8 pages",
  abstract =     "The automatic synthesis of aesthetically pleasing
                 images is investigated. Genetic programming with
                 multiobjective fitness evaluation is used to evolve
                 procedural texture formulae. With multi-objective
                 fitness testing, candidate textures are evaluated
                 according to multiple criteria. Each criteria
                 designates a dimension of a multi-dimensional fitness
                 space. The main feature test uses Ralph's model of
                 aesthetics. This aesthetic model is based on empirical
                 analyses of ne art, in which analysed art work exhibits
                 bell curve distributions of colour gradients.
                 Subjectively speaking, this bell-curve gradient
                 measurement tends to favour images that have harmonious
                 and balanced visual characteristics. Another feature
                 test is colour histogram scoring. This test permits
                 some control of the color composition, by matching a
                 candidate texture's color composition with the colour
                 histogram of a target image. This target image may be a
                 digital image of another artwork. We found that the use
                 of the bell curve model often resulted in images that
                 were harmonious and easy-on-the-eyes. Without the use
                 of the model, generated images were often too chaotic
                 or boring. Although our approach does not guarantee
                 aesthetically pleasing results, it does increase",
  notes =        "WCCI 2006 - A joint meeting of the IEEE, the EPS, and
                 the IEE.

                 IEEE Catalog Number: 06TH8846D",

Genetic Programming entries for Brian J Ross William Ralph Hai Zong