Noise-adaptive edge-preserving image restoration algorithm

Sung Cheol Park, Moon Gi Kang

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Most edge-preserving image restoration algorithms preserve discontinuities that are larger than a prescribed threshold value, therefore noise components whose differences in neighboring pixels are larger than the threshold become amplified unintentionally. We propose a noise-adaptive edge-preserving image restoration algorithm based on a Markov random field image model. The proposed potential function is controlled by the weighting function to adaptively incorporate the discontinuities into the solution. To avoid undesirable amplification of the noise, we introduce a noise-adaptive threshold to each pixel difference. As a result, the potential function varies its shape from a quadratic form to a concave form according to the amount of noise added to each pixel. In doing so, high-frequency components caused by strong noise are relatively more smoothed as with the quadratic potential function used, while edge components that have a small noise intensity are well preserved. The smoothing functional to be minimized is formulated to have a global minimizer in spite of its nonlinearity by enforcing the convergence and convexity requirements. The effectiveness of the proposed algorithm is demonstrated experimentally.

Original languageEnglish
Pages (from-to)3124-3137
Number of pages14
JournalOptical Engineering
Volume39
Issue number12
DOIs
Publication statusPublished - 2000 Dec 1

Fingerprint

Image reconstruction
restoration
preserving
Pixels
pixels
thresholds
discontinuity
Amplification
convexity
weighting functions
noise intensity
smoothing
nonlinearity
requirements

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Engineering(all)

Cite this

Park, Sung Cheol ; Kang, Moon Gi. / Noise-adaptive edge-preserving image restoration algorithm. In: Optical Engineering. 2000 ; Vol. 39, No. 12. pp. 3124-3137.
@article{256f35faf27944b696f342d15120db17,
title = "Noise-adaptive edge-preserving image restoration algorithm",
abstract = "Most edge-preserving image restoration algorithms preserve discontinuities that are larger than a prescribed threshold value, therefore noise components whose differences in neighboring pixels are larger than the threshold become amplified unintentionally. We propose a noise-adaptive edge-preserving image restoration algorithm based on a Markov random field image model. The proposed potential function is controlled by the weighting function to adaptively incorporate the discontinuities into the solution. To avoid undesirable amplification of the noise, we introduce a noise-adaptive threshold to each pixel difference. As a result, the potential function varies its shape from a quadratic form to a concave form according to the amount of noise added to each pixel. In doing so, high-frequency components caused by strong noise are relatively more smoothed as with the quadratic potential function used, while edge components that have a small noise intensity are well preserved. The smoothing functional to be minimized is formulated to have a global minimizer in spite of its nonlinearity by enforcing the convergence and convexity requirements. The effectiveness of the proposed algorithm is demonstrated experimentally.",
author = "Park, {Sung Cheol} and Kang, {Moon Gi}",
year = "2000",
month = "12",
day = "1",
doi = "10.1117/1.1320976",
language = "English",
volume = "39",
pages = "3124--3137",
journal = "Optical Engineering",
issn = "0091-3286",
publisher = "SPIE",
number = "12",

}

Noise-adaptive edge-preserving image restoration algorithm. / Park, Sung Cheol; Kang, Moon Gi.

In: Optical Engineering, Vol. 39, No. 12, 01.12.2000, p. 3124-3137.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Noise-adaptive edge-preserving image restoration algorithm

AU - Park, Sung Cheol

AU - Kang, Moon Gi

PY - 2000/12/1

Y1 - 2000/12/1

N2 - Most edge-preserving image restoration algorithms preserve discontinuities that are larger than a prescribed threshold value, therefore noise components whose differences in neighboring pixels are larger than the threshold become amplified unintentionally. We propose a noise-adaptive edge-preserving image restoration algorithm based on a Markov random field image model. The proposed potential function is controlled by the weighting function to adaptively incorporate the discontinuities into the solution. To avoid undesirable amplification of the noise, we introduce a noise-adaptive threshold to each pixel difference. As a result, the potential function varies its shape from a quadratic form to a concave form according to the amount of noise added to each pixel. In doing so, high-frequency components caused by strong noise are relatively more smoothed as with the quadratic potential function used, while edge components that have a small noise intensity are well preserved. The smoothing functional to be minimized is formulated to have a global minimizer in spite of its nonlinearity by enforcing the convergence and convexity requirements. The effectiveness of the proposed algorithm is demonstrated experimentally.

AB - Most edge-preserving image restoration algorithms preserve discontinuities that are larger than a prescribed threshold value, therefore noise components whose differences in neighboring pixels are larger than the threshold become amplified unintentionally. We propose a noise-adaptive edge-preserving image restoration algorithm based on a Markov random field image model. The proposed potential function is controlled by the weighting function to adaptively incorporate the discontinuities into the solution. To avoid undesirable amplification of the noise, we introduce a noise-adaptive threshold to each pixel difference. As a result, the potential function varies its shape from a quadratic form to a concave form according to the amount of noise added to each pixel. In doing so, high-frequency components caused by strong noise are relatively more smoothed as with the quadratic potential function used, while edge components that have a small noise intensity are well preserved. The smoothing functional to be minimized is formulated to have a global minimizer in spite of its nonlinearity by enforcing the convergence and convexity requirements. The effectiveness of the proposed algorithm is demonstrated experimentally.

UR - http://www.scopus.com/inward/record.url?scp=0034428595&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034428595&partnerID=8YFLogxK

U2 - 10.1117/1.1320976

DO - 10.1117/1.1320976

M3 - Article

AN - SCOPUS:0034428595

VL - 39

SP - 3124

EP - 3137

JO - Optical Engineering

JF - Optical Engineering

SN - 0091-3286

IS - 12

ER -