Adaptive image decomposition into cartoon and texture parts optimized by the orthogonality criterion

Dniel Szolgay, T. Szirányi

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In this paper, a new decomposition method is introduced that splits the image into geometric (or cartoon) and texture parts. Following a total variation based preprocesssing, the core of the proposed method is an anisotropic diffusion with an orthogonality-based parameter estimation and stopping condition. The quality criterion is defined by the theoretical assumption that the cartoon and the texture components of an image are orthogonal to each other. The presented method has been compared with other decomposition algorithms through visual and numerical evaluation to prove its superiority.

Original languageEnglish
Article number6175955
Pages (from-to)3405-3415
Number of pages11
JournalIEEE Transactions on Image Processing
Volume21
Issue number8
DOIs
Publication statusPublished - 2012

Fingerprint

Cartoons
Textures
Decomposition
Parameter estimation

Keywords

  • Anisotropic diffusion
  • image decomposition
  • quality criterion
  • texture segmentation
  • total variation

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software
  • Medicine(all)

Cite this

Adaptive image decomposition into cartoon and texture parts optimized by the orthogonality criterion. / Szolgay, Dniel; Szirányi, T.

In: IEEE Transactions on Image Processing, Vol. 21, No. 8, 6175955, 2012, p. 3405-3415.

Research output: Contribution to journalArticle

@article{4fdcc74bd41b4cb0912f45a1c8a5c314,
title = "Adaptive image decomposition into cartoon and texture parts optimized by the orthogonality criterion",
abstract = "In this paper, a new decomposition method is introduced that splits the image into geometric (or cartoon) and texture parts. Following a total variation based preprocesssing, the core of the proposed method is an anisotropic diffusion with an orthogonality-based parameter estimation and stopping condition. The quality criterion is defined by the theoretical assumption that the cartoon and the texture components of an image are orthogonal to each other. The presented method has been compared with other decomposition algorithms through visual and numerical evaluation to prove its superiority.",
keywords = "Anisotropic diffusion, image decomposition, quality criterion, texture segmentation, total variation",
author = "Dniel Szolgay and T. Szir{\'a}nyi",
year = "2012",
doi = "10.1109/TIP.2012.2192128",
language = "English",
volume = "21",
pages = "3405--3415",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "8",

}

TY - JOUR

T1 - Adaptive image decomposition into cartoon and texture parts optimized by the orthogonality criterion

AU - Szolgay, Dniel

AU - Szirányi, T.

PY - 2012

Y1 - 2012

N2 - In this paper, a new decomposition method is introduced that splits the image into geometric (or cartoon) and texture parts. Following a total variation based preprocesssing, the core of the proposed method is an anisotropic diffusion with an orthogonality-based parameter estimation and stopping condition. The quality criterion is defined by the theoretical assumption that the cartoon and the texture components of an image are orthogonal to each other. The presented method has been compared with other decomposition algorithms through visual and numerical evaluation to prove its superiority.

AB - In this paper, a new decomposition method is introduced that splits the image into geometric (or cartoon) and texture parts. Following a total variation based preprocesssing, the core of the proposed method is an anisotropic diffusion with an orthogonality-based parameter estimation and stopping condition. The quality criterion is defined by the theoretical assumption that the cartoon and the texture components of an image are orthogonal to each other. The presented method has been compared with other decomposition algorithms through visual and numerical evaluation to prove its superiority.

KW - Anisotropic diffusion

KW - image decomposition

KW - quality criterion

KW - texture segmentation

KW - total variation

UR - http://www.scopus.com/inward/record.url?scp=84864152682&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864152682&partnerID=8YFLogxK

U2 - 10.1109/TIP.2012.2192128

DO - 10.1109/TIP.2012.2192128

M3 - Article

C2 - 22481819

AN - SCOPUS:84864152682

VL - 21

SP - 3405

EP - 3415

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 8

M1 - 6175955

ER -