Image denoising with morphology- and size-adaptive block-matching transform domain filtering

Yingkun Hou, Dinggang Shen

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

BM3D is a state-of-the-art image denoising method. Its denoised results in the regions with strong edges can often be better than in the regions with smooth or weak edges, due to more accurate block-matching for the strong-edge regions. So using adaptive block sizes on different image regions may result in better image denoising. Based on these observations, in this paper, we first partition each image into regions belonging to one of the three morphological components, i.e., contour, texture, and smooth components, according to the regional energy of alternating current (AC) coefficients of discrete cosine transform (DCT). Then, we can adaptively determine the block size for each morphological component. Specifically, we use the smallest block size for the contour components, the medium block size for the texture components, and the largest block size for the smooth components. To better preserve image details, we also use a multi-stage strategy to implement image denoising, where every stage is similar to the BM3D method, except using adaptive sizes and different transform dimensions. Experimental results show that our proposed algorithm can achieve higher PSNR and MSSIM values than the BM3D method, and also better visual quality of denoised images than by the BM3D method and some other existing state-of-the-art methods.

Original languageEnglish
Article number59
JournalEurasip Journal on Image and Video Processing
Volume2018
Issue number1
DOIs
Publication statusPublished - 2018 Dec 1

Fingerprint

Image denoising
Textures
Discrete cosine transforms

Keywords

  • Block-matching
  • Image denoising
  • Morphological component
  • Size-adaptive filtering

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems
  • Electrical and Electronic Engineering

Cite this

Image denoising with morphology- and size-adaptive block-matching transform domain filtering. / Hou, Yingkun; Shen, Dinggang.

In: Eurasip Journal on Image and Video Processing, Vol. 2018, No. 1, 59, 01.12.2018.

Research output: Contribution to journalArticle

@article{77bbd1ad54b7415eb7ea366b714e8f9c,
title = "Image denoising with morphology- and size-adaptive block-matching transform domain filtering",
abstract = "BM3D is a state-of-the-art image denoising method. Its denoised results in the regions with strong edges can often be better than in the regions with smooth or weak edges, due to more accurate block-matching for the strong-edge regions. So using adaptive block sizes on different image regions may result in better image denoising. Based on these observations, in this paper, we first partition each image into regions belonging to one of the three morphological components, i.e., contour, texture, and smooth components, according to the regional energy of alternating current (AC) coefficients of discrete cosine transform (DCT). Then, we can adaptively determine the block size for each morphological component. Specifically, we use the smallest block size for the contour components, the medium block size for the texture components, and the largest block size for the smooth components. To better preserve image details, we also use a multi-stage strategy to implement image denoising, where every stage is similar to the BM3D method, except using adaptive sizes and different transform dimensions. Experimental results show that our proposed algorithm can achieve higher PSNR and MSSIM values than the BM3D method, and also better visual quality of denoised images than by the BM3D method and some other existing state-of-the-art methods.",
keywords = "Block-matching, Image denoising, Morphological component, Size-adaptive filtering",
author = "Yingkun Hou and Dinggang Shen",
year = "2018",
month = "12",
day = "1",
doi = "10.1186/s13640-018-0301-y",
language = "English",
volume = "2018",
journal = "Eurasip Journal on Image and Video Processing",
issn = "1687-5176",
publisher = "Springer Publishing Company",
number = "1",

}

TY - JOUR

T1 - Image denoising with morphology- and size-adaptive block-matching transform domain filtering

AU - Hou, Yingkun

AU - Shen, Dinggang

PY - 2018/12/1

Y1 - 2018/12/1

N2 - BM3D is a state-of-the-art image denoising method. Its denoised results in the regions with strong edges can often be better than in the regions with smooth or weak edges, due to more accurate block-matching for the strong-edge regions. So using adaptive block sizes on different image regions may result in better image denoising. Based on these observations, in this paper, we first partition each image into regions belonging to one of the three morphological components, i.e., contour, texture, and smooth components, according to the regional energy of alternating current (AC) coefficients of discrete cosine transform (DCT). Then, we can adaptively determine the block size for each morphological component. Specifically, we use the smallest block size for the contour components, the medium block size for the texture components, and the largest block size for the smooth components. To better preserve image details, we also use a multi-stage strategy to implement image denoising, where every stage is similar to the BM3D method, except using adaptive sizes and different transform dimensions. Experimental results show that our proposed algorithm can achieve higher PSNR and MSSIM values than the BM3D method, and also better visual quality of denoised images than by the BM3D method and some other existing state-of-the-art methods.

AB - BM3D is a state-of-the-art image denoising method. Its denoised results in the regions with strong edges can often be better than in the regions with smooth or weak edges, due to more accurate block-matching for the strong-edge regions. So using adaptive block sizes on different image regions may result in better image denoising. Based on these observations, in this paper, we first partition each image into regions belonging to one of the three morphological components, i.e., contour, texture, and smooth components, according to the regional energy of alternating current (AC) coefficients of discrete cosine transform (DCT). Then, we can adaptively determine the block size for each morphological component. Specifically, we use the smallest block size for the contour components, the medium block size for the texture components, and the largest block size for the smooth components. To better preserve image details, we also use a multi-stage strategy to implement image denoising, where every stage is similar to the BM3D method, except using adaptive sizes and different transform dimensions. Experimental results show that our proposed algorithm can achieve higher PSNR and MSSIM values than the BM3D method, and also better visual quality of denoised images than by the BM3D method and some other existing state-of-the-art methods.

KW - Block-matching

KW - Image denoising

KW - Morphological component

KW - Size-adaptive filtering

UR - http://www.scopus.com/inward/record.url?scp=85050373430&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050373430&partnerID=8YFLogxK

U2 - 10.1186/s13640-018-0301-y

DO - 10.1186/s13640-018-0301-y

M3 - Article

AN - SCOPUS:85050373430

VL - 2018

JO - Eurasip Journal on Image and Video Processing

JF - Eurasip Journal on Image and Video Processing

SN - 1687-5176

IS - 1

M1 - 59

ER -