Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

[CH+05]  Genetic Paint: A Search for Salient Paintings

Collomosse:2005:GPS (In proceedings)
Author(s)Collomosse J. and Hall P.
Title« Genetic Paint: A Search for Salient Paintings »
InApplications on Evolutionary Computing: EvoWorkkshops 2005: EvoBIO, EvoCOMNET, EvoHOT, EvoIASP, EvoMUSART, and EvoSTOC
SeriesLecture Notes in Computer Science
Volume3449
Page(s)437--447
Year2005
URLhttp://www.springerlink.com/link.asp?id=rddmddxpbq5kctnv

Abstract
The contribution of this paper is a novel non-photorealistic rendering (NPR) algorithm for rendering real images in an impasto painterly style. We argue that figurative artworks are salience maps, and develop a novel painting algorithm that uses a genetic algorithm (GA) to search the space of possible paintings for a given image, so approaching an ``optimal'' artwork in which salient detail is conserved and non-salient detail is attenuated. We demonstrate the results of our technique on a wide range of images, illustrating both the improved control over level of detail due to our salience adaptive painting approach, and the benefits gained by subsequent relaxation of the painting using the GA.

BibTeX code
@inproceedings{Collomosse:2005:GPS,
  opteditor = {Franz Rothlauf et al.},
  optpostscript = {},
  optaddress = {},
  optorganization = {},
  author = {John P. Collomosse and Peter M. Hall},
  optkey = {},
  series = LNICS,
  optannote = {},
  url = {http://www.springerlink.com/link.asp?id=rddmddxpbq5kctnv},
  localfile = {papers/Collomosse.2005.GPS.pdf},
  optpublisher = {},
  optisbn = {},
  optkeywords = {},
  doi = {http://dx.doi.org/10.1007/b106856},
  optmonth = {},
  optciteseer = {},
  volume = {3449},
  optcrossref = {},
  optwww = {},
  booktitle = {Applications on Evolutionary Computing: EvoWorkkshops 2005:
               EvoBIO, EvoCOMNET, EvoHOT, EvoIASP, EvoMUSART, and EvoSTOC},
  optnumber = {},
  abstract = {The contribution of this paper is a novel non-photorealistic
              rendering (NPR) algorithm for rendering real images in an impasto
              painterly style. We argue that figurative artworks are salience
              maps, and develop a novel painting algorithm that uses a genetic
              algorithm (GA) to search the space of possible paintings for a
              given image, so approaching an ``optimal'' artwork in which
              salient detail is conserved and non-salient detail is attenuated.
              We demonstrate the results of our technique on a wide range of
              images, illustrating both the improved control over level of
              detail due to our salience adaptive painting approach, and the
              benefits gained by subsequent relaxation of the painting using the
              GA.},
  title = {{G}enetic {P}aint: {A} {S}earch for {S}alient {P}aintings},
  year = {2005},
  pages = {437--447},
}

 Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

Submit a bug

This document was generated by bib2html 3.3.
Copyright © 1998-05 Stéphane GALLAND (under the GNU General Public License)

Valid HTML 4.01!Valid CSS!