Optimal noise removal using an adaptive Wiener filter based on a locally stationary Gaussian mixture distribution model for images

Nobumoto Yamane, Yoshitaka Morikawa, Youichi Kawakami, Hidekazu Takahashi

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This paper proposes an adaptive Wiener filter (AWF) based on the Gaussian mixture distribution model (GMM) as a realization of an optimum restoration filter. The proposed method is a kind of simple adaptive WF that classifies image blocks according to their local statistical properties and selects a matched WF from a class of a priori deduced WFs. In this method, the optimum filter is realized based on the fact that the minimum mean square error filter is reduced to a WF when the image and noise signals are both Gaussian. In addition, the probability distribution function of the signals in each class can be transformed to Gaussian by using the GMM as a statistical model for the image. In order to improve the accuracy of variance estimation and to reduce the computational complexity in deducing the WFs, a universal mixture model obtained from various kinds of training images is used as the underlying mixture model. In this paper, in restoring images corrupted with white noise, the method of estimating the covariance matrices in locally stationary processes and the method of designing the mixture model are studied, and the adaptive WF is designed. Finally, simulation results show the efficiency of the proposed method compared with conventional methods.

Original languageEnglish
Pages (from-to)49-60
Number of pages12
JournalElectronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi)
Volume87
Issue number1
DOIs
Publication statusPublished - Jan 2004

Fingerprint

Adaptive filters
White noise
Covariance matrix
Mean square error
Probability distributions
Restoration
Distribution functions
Computational complexity

Keywords

  • Gaussian mixture distribution model (GMM)
  • Minimum mean square error (MMSE) filter
  • Noise removal filter
  • Optimal restoration filter
  • Wiener filter

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

@article{0907ff077cdd4f1490ba1a1513c857ff,
title = "Optimal noise removal using an adaptive Wiener filter based on a locally stationary Gaussian mixture distribution model for images",
abstract = "This paper proposes an adaptive Wiener filter (AWF) based on the Gaussian mixture distribution model (GMM) as a realization of an optimum restoration filter. The proposed method is a kind of simple adaptive WF that classifies image blocks according to their local statistical properties and selects a matched WF from a class of a priori deduced WFs. In this method, the optimum filter is realized based on the fact that the minimum mean square error filter is reduced to a WF when the image and noise signals are both Gaussian. In addition, the probability distribution function of the signals in each class can be transformed to Gaussian by using the GMM as a statistical model for the image. In order to improve the accuracy of variance estimation and to reduce the computational complexity in deducing the WFs, a universal mixture model obtained from various kinds of training images is used as the underlying mixture model. In this paper, in restoring images corrupted with white noise, the method of estimating the covariance matrices in locally stationary processes and the method of designing the mixture model are studied, and the adaptive WF is designed. Finally, simulation results show the efficiency of the proposed method compared with conventional methods.",
keywords = "Gaussian mixture distribution model (GMM), Minimum mean square error (MMSE) filter, Noise removal filter, Optimal restoration filter, Wiener filter",
author = "Nobumoto Yamane and Yoshitaka Morikawa and Youichi Kawakami and Hidekazu Takahashi",
year = "2004",
month = "1",
doi = "10.1002/ecjc.10082",
language = "English",
volume = "87",
pages = "49--60",
journal = "Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi)",
issn = "1042-0967",
publisher = "John Wiley and Sons Inc.",
number = "1",

}

TY - JOUR

T1 - Optimal noise removal using an adaptive Wiener filter based on a locally stationary Gaussian mixture distribution model for images

AU - Yamane, Nobumoto

AU - Morikawa, Yoshitaka

AU - Kawakami, Youichi

AU - Takahashi, Hidekazu

PY - 2004/1

Y1 - 2004/1

N2 - This paper proposes an adaptive Wiener filter (AWF) based on the Gaussian mixture distribution model (GMM) as a realization of an optimum restoration filter. The proposed method is a kind of simple adaptive WF that classifies image blocks according to their local statistical properties and selects a matched WF from a class of a priori deduced WFs. In this method, the optimum filter is realized based on the fact that the minimum mean square error filter is reduced to a WF when the image and noise signals are both Gaussian. In addition, the probability distribution function of the signals in each class can be transformed to Gaussian by using the GMM as a statistical model for the image. In order to improve the accuracy of variance estimation and to reduce the computational complexity in deducing the WFs, a universal mixture model obtained from various kinds of training images is used as the underlying mixture model. In this paper, in restoring images corrupted with white noise, the method of estimating the covariance matrices in locally stationary processes and the method of designing the mixture model are studied, and the adaptive WF is designed. Finally, simulation results show the efficiency of the proposed method compared with conventional methods.

AB - This paper proposes an adaptive Wiener filter (AWF) based on the Gaussian mixture distribution model (GMM) as a realization of an optimum restoration filter. The proposed method is a kind of simple adaptive WF that classifies image blocks according to their local statistical properties and selects a matched WF from a class of a priori deduced WFs. In this method, the optimum filter is realized based on the fact that the minimum mean square error filter is reduced to a WF when the image and noise signals are both Gaussian. In addition, the probability distribution function of the signals in each class can be transformed to Gaussian by using the GMM as a statistical model for the image. In order to improve the accuracy of variance estimation and to reduce the computational complexity in deducing the WFs, a universal mixture model obtained from various kinds of training images is used as the underlying mixture model. In this paper, in restoring images corrupted with white noise, the method of estimating the covariance matrices in locally stationary processes and the method of designing the mixture model are studied, and the adaptive WF is designed. Finally, simulation results show the efficiency of the proposed method compared with conventional methods.

KW - Gaussian mixture distribution model (GMM)

KW - Minimum mean square error (MMSE) filter

KW - Noise removal filter

KW - Optimal restoration filter

KW - Wiener filter

UR - http://www.scopus.com/inward/record.url?scp=0142091635&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0142091635&partnerID=8YFLogxK

U2 - 10.1002/ecjc.10082

DO - 10.1002/ecjc.10082

M3 - Article

AN - SCOPUS:0142091635

VL - 87

SP - 49

EP - 60

JO - Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi)

JF - Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi)

SN - 1042-0967

IS - 1

ER -