Affine-invariant texture classification

D. Chetverikov, Zoltán Földvári

Research output: Chapter in Book/Report/Conference proceedingChapter

6 Citations (Scopus)

Abstract

In content-based image retrieval, a texture pattern may appear in a wide range of 3D views. Affine transformation is an approximation frequently used in practice to represent the variation of a pattern. The existing approaches to texture classification cannot cope with this variation. We use pattern regularity to define an ajfine-invariant feature vector and apply it to classification of structured textures under the orthographic projection, an important subset of affine transformations. The proposed approach achieves 85% accuracy for 18 patterns.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages889-892
Number of pages4
Volume15
Edition3
Publication statusPublished - 2000

Fingerprint

Textures
Image retrieval

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Cite this

Chetverikov, D., & Földvári, Z. (2000). Affine-invariant texture classification. In Proceedings - International Conference on Pattern Recognition (3 ed., Vol. 15, pp. 889-892)

Affine-invariant texture classification. / Chetverikov, D.; Földvári, Zoltán.

Proceedings - International Conference on Pattern Recognition. Vol. 15 3. ed. 2000. p. 889-892.

Research output: Chapter in Book/Report/Conference proceedingChapter

Chetverikov, D & Földvári, Z 2000, Affine-invariant texture classification. in Proceedings - International Conference on Pattern Recognition. 3 edn, vol. 15, pp. 889-892.
Chetverikov D, Földvári Z. Affine-invariant texture classification. In Proceedings - International Conference on Pattern Recognition. 3 ed. Vol. 15. 2000. p. 889-892
Chetverikov, D. ; Földvári, Zoltán. / Affine-invariant texture classification. Proceedings - International Conference on Pattern Recognition. Vol. 15 3. ed. 2000. pp. 889-892
@inbook{f5bf9762ea05435caefcb79437f39314,
title = "Affine-invariant texture classification",
abstract = "In content-based image retrieval, a texture pattern may appear in a wide range of 3D views. Affine transformation is an approximation frequently used in practice to represent the variation of a pattern. The existing approaches to texture classification cannot cope with this variation. We use pattern regularity to define an ajfine-invariant feature vector and apply it to classification of structured textures under the orthographic projection, an important subset of affine transformations. The proposed approach achieves 85{\%} accuracy for 18 patterns.",
author = "D. Chetverikov and Zolt{\'a}n F{\"o}ldv{\'a}ri",
year = "2000",
language = "English",
volume = "15",
pages = "889--892",
booktitle = "Proceedings - International Conference on Pattern Recognition",
edition = "3",

}

TY - CHAP

T1 - Affine-invariant texture classification

AU - Chetverikov, D.

AU - Földvári, Zoltán

PY - 2000

Y1 - 2000

N2 - In content-based image retrieval, a texture pattern may appear in a wide range of 3D views. Affine transformation is an approximation frequently used in practice to represent the variation of a pattern. The existing approaches to texture classification cannot cope with this variation. We use pattern regularity to define an ajfine-invariant feature vector and apply it to classification of structured textures under the orthographic projection, an important subset of affine transformations. The proposed approach achieves 85% accuracy for 18 patterns.

AB - In content-based image retrieval, a texture pattern may appear in a wide range of 3D views. Affine transformation is an approximation frequently used in practice to represent the variation of a pattern. The existing approaches to texture classification cannot cope with this variation. We use pattern regularity to define an ajfine-invariant feature vector and apply it to classification of structured textures under the orthographic projection, an important subset of affine transformations. The proposed approach achieves 85% accuracy for 18 patterns.

UR - http://www.scopus.com/inward/record.url?scp=33750924981&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750924981&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:33750924981

VL - 15

SP - 889

EP - 892

BT - Proceedings - International Conference on Pattern Recognition

ER -