Genetic paint: A search for salient paintings

J P Collomosse, P M Hall

Research output: Chapter in Book/Report/Conference proceedingChapter

  • 22 Citations

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.
LanguageEnglish
Title of host publicationApplications of Evolutionary Computing, Proceedings
Pages437-447
Number of pages11
Volume3449
StatusPublished - 2005

Publication series

NameLecture Notes in Computer Science

Fingerprint

Painting
Paint
Genetic algorithms

Cite this

Collomosse, J. P., & Hall, P. M. (2005). Genetic paint: A search for salient paintings. In Applications of Evolutionary Computing, Proceedings (Vol. 3449, pp. 437-447). (Lecture Notes in Computer Science).

Genetic paint: A search for salient paintings. / Collomosse, J P; Hall, P M.

Applications of Evolutionary Computing, Proceedings. Vol. 3449 2005. p. 437-447 (Lecture Notes in Computer Science).

Research output: Chapter in Book/Report/Conference proceedingChapter

Collomosse, JP & Hall, PM 2005, Genetic paint: A search for salient paintings. in Applications of Evolutionary Computing, Proceedings. vol. 3449, Lecture Notes in Computer Science, pp. 437-447.
Collomosse JP, Hall PM. Genetic paint: A search for salient paintings. In Applications of Evolutionary Computing, Proceedings. Vol. 3449. 2005. p. 437-447. (Lecture Notes in Computer Science).
Collomosse, J P ; Hall, P M. / Genetic paint: A search for salient paintings. Applications of Evolutionary Computing, Proceedings. Vol. 3449 2005. pp. 437-447 (Lecture Notes in Computer Science).
@inbook{3420b8919f124f6da8d5d3d898ea7fd2,
title = "Genetic paint: A search for salient paintings",
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.",
author = "Collomosse, {J P} and Hall, {P M}",
note = "ID number: ISI:000229211900044",
year = "2005",
language = "English",
isbn = "0302-9743",
volume = "3449",
series = "Lecture Notes in Computer Science",
pages = "437--447",
booktitle = "Applications of Evolutionary Computing, Proceedings",

}

TY - CHAP

T1 - Genetic paint: A search for salient paintings

AU - Collomosse,J P

AU - Hall,P M

N1 - ID number: ISI:000229211900044

PY - 2005

Y1 - 2005

N2 - 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.

AB - 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.

M3 - Chapter

SN - 0302-9743

VL - 3449

T3 - Lecture Notes in Computer Science

SP - 437

EP - 447

BT - Applications of Evolutionary Computing, Proceedings

ER -