Combining self-learning based super-resolution with denoising for noisy images

Oh Young Lee, Jae Won Lee, Jong-Ok Kim

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we propose a new learning based joint Super-Resolution (SR) and denoising algorithm for noisy images. The individual processing of denoising and SR when super-resolving a noisy image has drawbacks such as noise amplification, blurring and SR performance reduction. In the proposed joint method, principal component analysis (PCA) based denoising is closely combined with a self-learning SR framework in order to minimize the SR visual quality degradation caused by noise. Experimental results show that the joint method achieves an SR image quality improvement in terms of noise and blurring, when compared with the state-of-the-art joint method and sequential combinations of individual denoising and SR.

Original languageEnglish
Pages (from-to)66-76
Number of pages11
JournalJournal of Visual Communication and Image Representation
Volume48
DOIs
Publication statusPublished - 2017 Oct 1

Fingerprint

Principal component analysis
Image quality
Amplification
Degradation
Processing

Keywords

  • Denoising
  • Image super-resolution
  • Noisy image
  • PCA
  • Self-learning

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Combining self-learning based super-resolution with denoising for noisy images. / Lee, Oh Young; Lee, Jae Won; Kim, Jong-Ok.

In: Journal of Visual Communication and Image Representation, Vol. 48, 01.10.2017, p. 66-76.

Research output: Contribution to journalArticle

@article{c04d3d6841414a1eb93340120360ab5e,
title = "Combining self-learning based super-resolution with denoising for noisy images",
abstract = "In this paper, we propose a new learning based joint Super-Resolution (SR) and denoising algorithm for noisy images. The individual processing of denoising and SR when super-resolving a noisy image has drawbacks such as noise amplification, blurring and SR performance reduction. In the proposed joint method, principal component analysis (PCA) based denoising is closely combined with a self-learning SR framework in order to minimize the SR visual quality degradation caused by noise. Experimental results show that the joint method achieves an SR image quality improvement in terms of noise and blurring, when compared with the state-of-the-art joint method and sequential combinations of individual denoising and SR.",
keywords = "Denoising, Image super-resolution, Noisy image, PCA, Self-learning",
author = "Lee, {Oh Young} and Lee, {Jae Won} and Jong-Ok Kim",
year = "2017",
month = "10",
day = "1",
doi = "10.1016/j.jvcir.2017.05.010",
language = "English",
volume = "48",
pages = "66--76",
journal = "Journal of Visual Communication and Image Representation",
issn = "1047-3203",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Combining self-learning based super-resolution with denoising for noisy images

AU - Lee, Oh Young

AU - Lee, Jae Won

AU - Kim, Jong-Ok

PY - 2017/10/1

Y1 - 2017/10/1

N2 - In this paper, we propose a new learning based joint Super-Resolution (SR) and denoising algorithm for noisy images. The individual processing of denoising and SR when super-resolving a noisy image has drawbacks such as noise amplification, blurring and SR performance reduction. In the proposed joint method, principal component analysis (PCA) based denoising is closely combined with a self-learning SR framework in order to minimize the SR visual quality degradation caused by noise. Experimental results show that the joint method achieves an SR image quality improvement in terms of noise and blurring, when compared with the state-of-the-art joint method and sequential combinations of individual denoising and SR.

AB - In this paper, we propose a new learning based joint Super-Resolution (SR) and denoising algorithm for noisy images. The individual processing of denoising and SR when super-resolving a noisy image has drawbacks such as noise amplification, blurring and SR performance reduction. In the proposed joint method, principal component analysis (PCA) based denoising is closely combined with a self-learning SR framework in order to minimize the SR visual quality degradation caused by noise. Experimental results show that the joint method achieves an SR image quality improvement in terms of noise and blurring, when compared with the state-of-the-art joint method and sequential combinations of individual denoising and SR.

KW - Denoising

KW - Image super-resolution

KW - Noisy image

KW - PCA

KW - Self-learning

UR - http://www.scopus.com/inward/record.url?scp=85020875990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020875990&partnerID=8YFLogxK

U2 - 10.1016/j.jvcir.2017.05.010

DO - 10.1016/j.jvcir.2017.05.010

M3 - Article

AN - SCOPUS:85020875990

VL - 48

SP - 66

EP - 76

JO - Journal of Visual Communication and Image Representation

JF - Journal of Visual Communication and Image Representation

SN - 1047-3203

ER -