A K Times Singular Value Decomposition Based Image Denoising Algorithm for DoFP Polarization Image Sensors with Gaussian Noise

Wenbin Ye, Shiting Li, Xiaojin Zhao, Abubakar Abubakar, Amine Bermak

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In this paper, we present a novel K times singular value decomposition (K-SVD) based denoising algorithm dedicated to the division-of-focal-plane (DoFP) polarization image sensors. The proposed method is based on sparse representation over trained dictionary. Using the proposed K-SVD algorithm to update the dictionary, the image content can be more effectively expressed. Compared with the previous denoising algorithms, the proposed implementation is capable of decomposing the input DoFP image as the optimum sparse combination of the dictionary elements, which are generated by orthogonal matching pursuit (OMP). This not only separates the Gaussian noise from the target DoFP image with a significantly elevated peak signal-tonoise ratio (PSNR), but also well-preserves the details of the original image. According to our extensive experimental results on various test images, the proposed algorithm outperforms the state-of-the-art principal component analysis (PCA) based denoising algorithm by 3dB in term of PSNR. Moreover, visual comparison results, which show excellent agreement with the PSNR results, are presented as well.

Original languageEnglish
JournalIEEE Sensors Journal
DOIs
Publication statusAccepted/In press - 11 Jun 2018

Fingerprint

Gaussian noise (electronic)
Image denoising
Singular value decomposition
random noise
Image sensors
division
Polarization
decomposition
Glossaries
dictionaries
sensors
polarization
Principal component analysis
principal components analysis

Keywords

  • Dictionaries
  • division of focal plane
  • image denoising
  • Image sensors
  • Interpolation
  • Matching pursuit algorithms
  • Noise reduction
  • Polarization image sensor
  • Sensors
  • singular value decomposition
  • Training

ASJC Scopus subject areas

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

A K Times Singular Value Decomposition Based Image Denoising Algorithm for DoFP Polarization Image Sensors with Gaussian Noise. / Ye, Wenbin; Li, Shiting; Zhao, Xiaojin; Abubakar, Abubakar; Bermak, Amine.

In: IEEE Sensors Journal, 11.06.2018.

Research output: Contribution to journalArticle

@article{b53da47cea064d9684b5b9f055e50ba3,
title = "A K Times Singular Value Decomposition Based Image Denoising Algorithm for DoFP Polarization Image Sensors with Gaussian Noise",
abstract = "In this paper, we present a novel K times singular value decomposition (K-SVD) based denoising algorithm dedicated to the division-of-focal-plane (DoFP) polarization image sensors. The proposed method is based on sparse representation over trained dictionary. Using the proposed K-SVD algorithm to update the dictionary, the image content can be more effectively expressed. Compared with the previous denoising algorithms, the proposed implementation is capable of decomposing the input DoFP image as the optimum sparse combination of the dictionary elements, which are generated by orthogonal matching pursuit (OMP). This not only separates the Gaussian noise from the target DoFP image with a significantly elevated peak signal-tonoise ratio (PSNR), but also well-preserves the details of the original image. According to our extensive experimental results on various test images, the proposed algorithm outperforms the state-of-the-art principal component analysis (PCA) based denoising algorithm by 3dB in term of PSNR. Moreover, visual comparison results, which show excellent agreement with the PSNR results, are presented as well.",
keywords = "Dictionaries, division of focal plane, image denoising, Image sensors, Interpolation, Matching pursuit algorithms, Noise reduction, Polarization image sensor, Sensors, singular value decomposition, Training",
author = "Wenbin Ye and Shiting Li and Xiaojin Zhao and Abubakar Abubakar and Amine Bermak",
year = "2018",
month = "6",
day = "11",
doi = "10.1109/JSEN.2018.2846672",
language = "English",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - A K Times Singular Value Decomposition Based Image Denoising Algorithm for DoFP Polarization Image Sensors with Gaussian Noise

AU - Ye, Wenbin

AU - Li, Shiting

AU - Zhao, Xiaojin

AU - Abubakar, Abubakar

AU - Bermak, Amine

PY - 2018/6/11

Y1 - 2018/6/11

N2 - In this paper, we present a novel K times singular value decomposition (K-SVD) based denoising algorithm dedicated to the division-of-focal-plane (DoFP) polarization image sensors. The proposed method is based on sparse representation over trained dictionary. Using the proposed K-SVD algorithm to update the dictionary, the image content can be more effectively expressed. Compared with the previous denoising algorithms, the proposed implementation is capable of decomposing the input DoFP image as the optimum sparse combination of the dictionary elements, which are generated by orthogonal matching pursuit (OMP). This not only separates the Gaussian noise from the target DoFP image with a significantly elevated peak signal-tonoise ratio (PSNR), but also well-preserves the details of the original image. According to our extensive experimental results on various test images, the proposed algorithm outperforms the state-of-the-art principal component analysis (PCA) based denoising algorithm by 3dB in term of PSNR. Moreover, visual comparison results, which show excellent agreement with the PSNR results, are presented as well.

AB - In this paper, we present a novel K times singular value decomposition (K-SVD) based denoising algorithm dedicated to the division-of-focal-plane (DoFP) polarization image sensors. The proposed method is based on sparse representation over trained dictionary. Using the proposed K-SVD algorithm to update the dictionary, the image content can be more effectively expressed. Compared with the previous denoising algorithms, the proposed implementation is capable of decomposing the input DoFP image as the optimum sparse combination of the dictionary elements, which are generated by orthogonal matching pursuit (OMP). This not only separates the Gaussian noise from the target DoFP image with a significantly elevated peak signal-tonoise ratio (PSNR), but also well-preserves the details of the original image. According to our extensive experimental results on various test images, the proposed algorithm outperforms the state-of-the-art principal component analysis (PCA) based denoising algorithm by 3dB in term of PSNR. Moreover, visual comparison results, which show excellent agreement with the PSNR results, are presented as well.

KW - Dictionaries

KW - division of focal plane

KW - image denoising

KW - Image sensors

KW - Interpolation

KW - Matching pursuit algorithms

KW - Noise reduction

KW - Polarization image sensor

KW - Sensors

KW - singular value decomposition

KW - Training

UR - http://www.scopus.com/inward/record.url?scp=85048589228&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048589228&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2018.2846672

DO - 10.1109/JSEN.2018.2846672

M3 - Article

AN - SCOPUS:85048589228

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

ER -