Refinement Techniques for Animated Evolutionary Photomosaics using Limited Tile Collections

Created by W.Langdon from gp-bibliography.bib Revision:1.4333

  author =       "Shahrul Badariah Mat Sah and Vic Ciesielski and 
                 Daryl D'Souza",
  title =        "Refinement Techniques for Animated Evolutionary
                 Photomosaics using Limited Tile Collections",
  booktitle =    "EvoMUSART",
  year =         "2010",
  editor =       "Cecilia {Di Chio} and Anthony Brabazon and 
                 Gianni A. {Di Caro} and Marc Ebner and Muddassar Farooq and 
                 Andreas Fink and Jorn Grahl and Gary Greenfield and 
                 Penousal Machado and Michael O'Neill and 
                 Ernesto Tarantino and Neil Urquhart",
  volume =       "6025",
  series =       "LNCS",
  pages =        "281--290",
  address =      "Istanbul",
  month =        "7-9 " # apr,
  organisation = "EvoStar",
  publisher =    "Springer",
  keywords =     "genetic algorithms, genetic programming,
                 Non-photorealistic rendering, animated evolved
                 photomosaic, evolved art, genetic art, digital art",
  isbn13 =       "978-3-642-12241-5",
  DOI =          "doi:10.1007/978-3-642-12242-2_29",
  abstract =     "An animated evolutionary photomosaic is produced from
                 a sequence of still or static photomosaics to evolve a
                 near match to a given target image. A static
                 photomosaic is composed of small digital images or
                 tiles, each having their own aesthetic value. If the
                 tiles are prepared manually, the tile collections are
                 typically small. This potentially limits the visual
                 quality of a photomosaic as there may not be sufficient
                 options for matching tiles. We investigate the use of
                 colour adjustment and tile size variation techniques
                 via genetic programming to improve the animated
                 photomosaics. The results show that colour adjustment
                 improved both visual quality and fitness. However, it
                 can produce strange looking tiles. Tile size variation
                 was able to focus on details in the target image but
                 produced slightly worse fitness values than an
                 equal-sized tiles approach. Combining these techniques
                 revealed that, regardless of the size of tiles, colour
                 adjustment was the dominant refinement. In conclusion,
                 each of these techniques is able to produce an
                 aesthetically different animation effect and presents a
                 better mechanism for generating photomosaics w",
  notes =        "EvoMUSART'2010 held in conjunction with EuroGP'2010
                 EvoCOP2010 EvoBIO2010",

Genetic Programming entries for Shahrul Badariah Mat Sah Victor Ciesielski Daryl J D'Souza