Generating contrast curves for texture regularity analysis

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Statistical approaches to texture use features that describe the distribution of intensities or local features but ignore their spatial interdependence. Structural approaches concentrate on the spatial interaction of elementary regions, local features, or intensities. In most of the structural methods, it is assumed that the examined texture pattern is more or less regular. Such methods are inappropriate for dealing with the gradual transition from regularity to randomness which is typical for the spectrum of natural textures. In this paper, an attempt is made to bridge the gap between statistical and structural texture analyzers. The contrast curve of a texture pattern is defined as the first moment of a co-occurrence matrix plotted as a function of the intersample distance. The curve is used as a texture descriptor. An algorithm is presented that generates the contrast curves of both regular and random textures in the framework of a simple, uniform model. The model has four parameters that are easy to interpret. The generated curves are fitted to the experimental ones, and certain combinations of the parameters of the best fitting curves are introduced to measure texture regularity.

Original languageEnglish
Pages (from-to)437-444
Number of pages8
JournalPattern Recognition Letters
Volume12
Issue number7
DOIs
Publication statusPublished - 1991

Fingerprint

Textures
Curve fitting

Keywords

  • curve fitting
  • Texture analysis
  • texture models
  • texture regularity

ASJC Scopus subject areas

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

Cite this

Generating contrast curves for texture regularity analysis. / Chetverikov, D.

In: Pattern Recognition Letters, Vol. 12, No. 7, 1991, p. 437-444.

Research output: Contribution to journalArticle

@article{80ef29a297e543aebf69533928418226,
title = "Generating contrast curves for texture regularity analysis",
abstract = "Statistical approaches to texture use features that describe the distribution of intensities or local features but ignore their spatial interdependence. Structural approaches concentrate on the spatial interaction of elementary regions, local features, or intensities. In most of the structural methods, it is assumed that the examined texture pattern is more or less regular. Such methods are inappropriate for dealing with the gradual transition from regularity to randomness which is typical for the spectrum of natural textures. In this paper, an attempt is made to bridge the gap between statistical and structural texture analyzers. The contrast curve of a texture pattern is defined as the first moment of a co-occurrence matrix plotted as a function of the intersample distance. The curve is used as a texture descriptor. An algorithm is presented that generates the contrast curves of both regular and random textures in the framework of a simple, uniform model. The model has four parameters that are easy to interpret. The generated curves are fitted to the experimental ones, and certain combinations of the parameters of the best fitting curves are introduced to measure texture regularity.",
keywords = "curve fitting, Texture analysis, texture models, texture regularity",
author = "D. Chetverikov",
year = "1991",
doi = "10.1016/0167-8655(91)90334-I",
language = "English",
volume = "12",
pages = "437--444",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",
number = "7",

}

TY - JOUR

T1 - Generating contrast curves for texture regularity analysis

AU - Chetverikov, D.

PY - 1991

Y1 - 1991

N2 - Statistical approaches to texture use features that describe the distribution of intensities or local features but ignore their spatial interdependence. Structural approaches concentrate on the spatial interaction of elementary regions, local features, or intensities. In most of the structural methods, it is assumed that the examined texture pattern is more or less regular. Such methods are inappropriate for dealing with the gradual transition from regularity to randomness which is typical for the spectrum of natural textures. In this paper, an attempt is made to bridge the gap between statistical and structural texture analyzers. The contrast curve of a texture pattern is defined as the first moment of a co-occurrence matrix plotted as a function of the intersample distance. The curve is used as a texture descriptor. An algorithm is presented that generates the contrast curves of both regular and random textures in the framework of a simple, uniform model. The model has four parameters that are easy to interpret. The generated curves are fitted to the experimental ones, and certain combinations of the parameters of the best fitting curves are introduced to measure texture regularity.

AB - Statistical approaches to texture use features that describe the distribution of intensities or local features but ignore their spatial interdependence. Structural approaches concentrate on the spatial interaction of elementary regions, local features, or intensities. In most of the structural methods, it is assumed that the examined texture pattern is more or less regular. Such methods are inappropriate for dealing with the gradual transition from regularity to randomness which is typical for the spectrum of natural textures. In this paper, an attempt is made to bridge the gap between statistical and structural texture analyzers. The contrast curve of a texture pattern is defined as the first moment of a co-occurrence matrix plotted as a function of the intersample distance. The curve is used as a texture descriptor. An algorithm is presented that generates the contrast curves of both regular and random textures in the framework of a simple, uniform model. The model has four parameters that are easy to interpret. The generated curves are fitted to the experimental ones, and certain combinations of the parameters of the best fitting curves are introduced to measure texture regularity.

KW - curve fitting

KW - Texture analysis

KW - texture models

KW - texture regularity

UR - http://www.scopus.com/inward/record.url?scp=0026313144&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026313144&partnerID=8YFLogxK

U2 - 10.1016/0167-8655(91)90334-I

DO - 10.1016/0167-8655(91)90334-I

M3 - Article

AN - SCOPUS:0026313144

VL - 12

SP - 437

EP - 444

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

IS - 7

ER -