Supervised genetic search for parameter selection in painterly rendering

J P Collomosse

Research output: Chapter in Book/Report/Conference proceedingChapter

8 Citations (Scopus)

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 nonexpert 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.
Original languageEnglish
Title of host publicationApplications of Evolutionary Computing, Proceedings
Pages599-610
Number of pages12
Volume3907
Publication statusPublished - 2006

Publication series

NameLecture Notes in Computer Science

Fingerprint

Painting
Specifications

Cite this

Collomosse, J. P. (2006). Supervised genetic search for parameter selection in painterly rendering. In Applications of Evolutionary Computing, Proceedings (Vol. 3907, pp. 599-610). (Lecture Notes in Computer Science).

Supervised genetic search for parameter selection in painterly rendering. / Collomosse, J P.

Applications of Evolutionary Computing, Proceedings. Vol. 3907 2006. p. 599-610 (Lecture Notes in Computer Science).

Research output: Chapter in Book/Report/Conference proceedingChapter

Collomosse, JP 2006, Supervised genetic search for parameter selection in painterly rendering. in Applications of Evolutionary Computing, Proceedings. vol. 3907, Lecture Notes in Computer Science, pp. 599-610.
Collomosse JP. Supervised genetic search for parameter selection in painterly rendering. In Applications of Evolutionary Computing, Proceedings. Vol. 3907. 2006. p. 599-610. (Lecture Notes in Computer Science).
Collomosse, J P. / Supervised genetic search for parameter selection in painterly rendering. Applications of Evolutionary Computing, Proceedings. Vol. 3907 2006. pp. 599-610 (Lecture Notes in Computer Science).
@inbook{b29b10192f8149e3ae2b8dc8a9884f0f,
title = "Supervised genetic search for parameter selection in painterly rendering",
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 nonexpert 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.",
author = "Collomosse, {J P}",
note = "ID number: ISI:000237228900057",
year = "2006",
language = "English",
isbn = "0302-9743",
volume = "3907",
series = "Lecture Notes in Computer Science",
pages = "599--610",
booktitle = "Applications of Evolutionary Computing, Proceedings",

}

TY - CHAP

T1 - Supervised genetic search for parameter selection in painterly rendering

AU - Collomosse, J P

N1 - ID number: ISI:000237228900057

PY - 2006

Y1 - 2006

N2 - 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 nonexpert 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.

AB - 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 nonexpert 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.

M3 - Chapter

SN - 0302-9743

VL - 3907

T3 - Lecture Notes in Computer Science

SP - 599

EP - 610

BT - Applications of Evolutionary Computing, Proceedings

ER -