Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

[Col06]  Supervised Genetic Search for Parameter Selection in Painterly Rendering

Collomosse:2006:SGS (In proceedings)
Author(s)Collomosse J.
Title« Supervised Genetic Search for Parameter Selection in Painterly Rendering »
InApplications of Evolutionary Computing, Proceedings of the Fourth European Workshop on Evolutionary Music and Art (EvoMUSART 2006 as part of EvoWorkshops 2006, April 10--12, 2006, Budapest, Hungary)
SeriesLecture Notes in Computer Science
Editor(s)Franz Rothlauf et al.
Volume3907
Page(s)599--610
Year2006
PublisherSpringer-Verlag
AddressBerlin · Heidelberg · New York
Editor(s)Franz Rothlauf et al.

Abstract
This paper investigates the feasibility of evolutionary search techniques as a mechanism for interactively exploring the design space of 2D painterly renderings. Although a growing body of painterly rendering literature exists, the large number of low-level configurable parameters that feature in contemporary algorithms can be counter-intuitive for non-expert users to set. In this paper we first describe a multi-resolution painting algorithm capable of transforming photographs into paintings at interactive speeds. We then present a supervised evolutionary search process in which the user scores paintings on their aesthetics to guide the specification of their desired painterly rendering. Using our system, nonexpert users are able to produce their desired aesthetic in approximately 20 mouse clicks --- around half an order of magnitude faster than manual specification of individual rendering parameters by trial and error.

BibTeX code
@inproceedings{Collomosse:2006:SGS,
  optpostscript = {},
  optorganization = {},
  author = {John P. Collomosse},
  optkey = {},
  series = LNICS,
  optannote = {},
  editor = {Franz Rothlauf et al.},
  address = SpringerAdr,
  localfile = {papers/Collomosse.2006.SGS.pdf},
  optisbn = {},
  publisher = SpringerPub,
  optkeywords = {},
  optmonth = {},
  optciteseer = {},
  doi = {http://dx.doi.org/10.1007/11732242},
  opturl = {},
  volume = {3907},
  optcrossref = {},
  optwww = {},
  booktitle = {Applications of Evolutionary Computing, Proceedings of the Fourth
               European Workshop on Evolutionary Music and Art (EvoMUSART 2006
               as part of EvoWorkshops 2006, April 10--12, 2006, Budapest,
               Hungary)},
  optnumber = {},
  abstract = {This paper investigates the feasibility of evolutionary search
              techniques as a mechanism for interactively exploring the design
              space of 2D painterly renderings. Although a growing body of
              painterly rendering literature exists, the large number of
              low-level configurable parameters that feature in contemporary
              algorithms can be counter-intuitive for non-expert users to set.
              In this paper we first describe a multi-resolution painting
              algorithm capable of transforming photographs into paintings at
              interactive speeds. We then present a supervised evolutionary
              search process in which the user scores paintings on their
              aesthetics to guide the specification of their desired painterly
              rendering. Using our system, nonexpert users are able to produce
              their desired aesthetic in approximately 20 mouse clicks ---
              around half an order of magnitude faster than manual specification
              of individual rendering parameters by trial and error.},
  title = {{S}upervised {G}enetic {S}earch for {P}arameter {S}election in
           {P}ainterly {R}endering},
  year = {2006},
  pages = {599--610},
}

 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!