Total variation-based image noise reduction with generalized fidelity function

Suk Ho Lee, Moon Gi Kang

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In this letter, we analyze the relationship between the change in the intensity value and the scale of an image feature, when a generalized function is used as the fidelity term in the total variation-based noise removal scheme. Based on the analysis, we propose a designing method of the fidelity function that results in any desired monotonic relationship between the intensity change and the scale. As an example, we designed a fidelity function that results in a larger contrast between the intensity change of a small scaled feature and that of a large scaled one than the original total variation-based noise removal scheme that uses the L2 norm as the fidelity function.

Original languageEnglish
Pages (from-to)832-835
Number of pages4
JournalIEEE Signal Processing Letters
Volume14
Issue number11
DOIs
Publication statusPublished - 2007 Nov 1

Fingerprint

Noise Reduction
Total Variation
Noise abatement
Fidelity
Noise Removal
Generalized Functions
Monotonic
Norm
Term
Relationships

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Signal Processing

Cite this

@article{74887a995ca347d09a91e909a24fe790,
title = "Total variation-based image noise reduction with generalized fidelity function",
abstract = "In this letter, we analyze the relationship between the change in the intensity value and the scale of an image feature, when a generalized function is used as the fidelity term in the total variation-based noise removal scheme. Based on the analysis, we propose a designing method of the fidelity function that results in any desired monotonic relationship between the intensity change and the scale. As an example, we designed a fidelity function that results in a larger contrast between the intensity change of a small scaled feature and that of a large scaled one than the original total variation-based noise removal scheme that uses the L2 norm as the fidelity function.",
author = "Lee, {Suk Ho} and Kang, {Moon Gi}",
year = "2007",
month = "11",
day = "1",
doi = "10.1109/LSP.2007.901697",
language = "English",
volume = "14",
pages = "832--835",
journal = "IEEE Signal Processing Letters",
issn = "1070-9908",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

Total variation-based image noise reduction with generalized fidelity function. / Lee, Suk Ho; Kang, Moon Gi.

In: IEEE Signal Processing Letters, Vol. 14, No. 11, 01.11.2007, p. 832-835.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Total variation-based image noise reduction with generalized fidelity function

AU - Lee, Suk Ho

AU - Kang, Moon Gi

PY - 2007/11/1

Y1 - 2007/11/1

N2 - In this letter, we analyze the relationship between the change in the intensity value and the scale of an image feature, when a generalized function is used as the fidelity term in the total variation-based noise removal scheme. Based on the analysis, we propose a designing method of the fidelity function that results in any desired monotonic relationship between the intensity change and the scale. As an example, we designed a fidelity function that results in a larger contrast between the intensity change of a small scaled feature and that of a large scaled one than the original total variation-based noise removal scheme that uses the L2 norm as the fidelity function.

AB - In this letter, we analyze the relationship between the change in the intensity value and the scale of an image feature, when a generalized function is used as the fidelity term in the total variation-based noise removal scheme. Based on the analysis, we propose a designing method of the fidelity function that results in any desired monotonic relationship between the intensity change and the scale. As an example, we designed a fidelity function that results in a larger contrast between the intensity change of a small scaled feature and that of a large scaled one than the original total variation-based noise removal scheme that uses the L2 norm as the fidelity function.

UR - http://www.scopus.com/inward/record.url?scp=36249030390&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36249030390&partnerID=8YFLogxK

U2 - 10.1109/LSP.2007.901697

DO - 10.1109/LSP.2007.901697

M3 - Article

VL - 14

SP - 832

EP - 835

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

IS - 11

ER -