An evolutionary system for near-regular texture synthesis

Fei Wu, Changshui Zhang, Jingrui He

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Near-regular texture is probably among the most difficult to handle in the texture synthesis area, because the synthesis must preserve the holistic structural property and the local randomness simultaneously. In this paper, motivated by the relationship between a near-regular texture image and an evolutionary system, we propose a novel texture synthesis algorithm. By defining individuals with appropriate attributes and behaviors, we convert the texture synthesis problem to an evolution process of an evolutionary system. It can achieve high-quality synthesized results on a large variety of near-regular textures without any extra overhead for memory and pretreatment, and the speed approaches real-time. Moreover, it can be easily generalized to deal with other kinds of textures.

Original languageEnglish (US)
Pages (from-to)2271-2282
Number of pages12
JournalPattern Recognition
Volume40
Issue number8
DOIs
StatePublished - Aug 2007
Externally publishedYes

Fingerprint

Textures
Structural properties
Data storage equipment

Keywords

  • Evolutionary system
  • Near-regular texture
  • Texture synthesis
  • Texture system
  • Unit pattern

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

An evolutionary system for near-regular texture synthesis. / Wu, Fei; Zhang, Changshui; He, Jingrui.

In: Pattern Recognition, Vol. 40, No. 8, 08.2007, p. 2271-2282.

Research output: Contribution to journalArticle

Wu, Fei ; Zhang, Changshui ; He, Jingrui. / An evolutionary system for near-regular texture synthesis. In: Pattern Recognition. 2007 ; Vol. 40, No. 8. pp. 2271-2282.
@article{0bc57897c2c24c90a1c5ee7a556fd2b0,
title = "An evolutionary system for near-regular texture synthesis",
abstract = "Near-regular texture is probably among the most difficult to handle in the texture synthesis area, because the synthesis must preserve the holistic structural property and the local randomness simultaneously. In this paper, motivated by the relationship between a near-regular texture image and an evolutionary system, we propose a novel texture synthesis algorithm. By defining individuals with appropriate attributes and behaviors, we convert the texture synthesis problem to an evolution process of an evolutionary system. It can achieve high-quality synthesized results on a large variety of near-regular textures without any extra overhead for memory and pretreatment, and the speed approaches real-time. Moreover, it can be easily generalized to deal with other kinds of textures.",
keywords = "Evolutionary system, Near-regular texture, Texture synthesis, Texture system, Unit pattern",
author = "Fei Wu and Changshui Zhang and Jingrui He",
year = "2007",
month = "8",
doi = "10.1016/j.patcog.2006.10.017",
language = "English (US)",
volume = "40",
pages = "2271--2282",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "8",

}

TY - JOUR

T1 - An evolutionary system for near-regular texture synthesis

AU - Wu, Fei

AU - Zhang, Changshui

AU - He, Jingrui

PY - 2007/8

Y1 - 2007/8

N2 - Near-regular texture is probably among the most difficult to handle in the texture synthesis area, because the synthesis must preserve the holistic structural property and the local randomness simultaneously. In this paper, motivated by the relationship between a near-regular texture image and an evolutionary system, we propose a novel texture synthesis algorithm. By defining individuals with appropriate attributes and behaviors, we convert the texture synthesis problem to an evolution process of an evolutionary system. It can achieve high-quality synthesized results on a large variety of near-regular textures without any extra overhead for memory and pretreatment, and the speed approaches real-time. Moreover, it can be easily generalized to deal with other kinds of textures.

AB - Near-regular texture is probably among the most difficult to handle in the texture synthesis area, because the synthesis must preserve the holistic structural property and the local randomness simultaneously. In this paper, motivated by the relationship between a near-regular texture image and an evolutionary system, we propose a novel texture synthesis algorithm. By defining individuals with appropriate attributes and behaviors, we convert the texture synthesis problem to an evolution process of an evolutionary system. It can achieve high-quality synthesized results on a large variety of near-regular textures without any extra overhead for memory and pretreatment, and the speed approaches real-time. Moreover, it can be easily generalized to deal with other kinds of textures.

KW - Evolutionary system

KW - Near-regular texture

KW - Texture synthesis

KW - Texture system

KW - Unit pattern

UR - http://www.scopus.com/inward/record.url?scp=34147131104&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34147131104&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2006.10.017

DO - 10.1016/j.patcog.2006.10.017

M3 - Article

VL - 40

SP - 2271

EP - 2282

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 8

ER -