Circular-vector based non-local SAR image denoising algorithm

Yu Chen Cai; Bao Jun Zhao; Lin Bo Tang

Circular-vector based non-local SAR image denoising algorithm

Yu Chen Cai, Bao Jun Zhao^*, Lin Bo Tang

^*Corresponding author for this work

School of Information and Electronics

Beijing Institute of Technology

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

A circular-vector based non-local SAR image denoising algorithm was proposed. Circular vectors were abstracted according to the main direction of the central pixel. Feature vectors were then calculated and the weights of similarity were obtained based on these feature vectors. The execution time and quality of rotation invariance were tested. The results show that the time complexity is significantly lower than the patch-based similarity matching algorithm in NL-Means, and the rotation invariance is also maintained. Experiments have verified that the proposed algorithm shows better similarity matching results comparing to NL-Means and competitive denoising results on PSNR and SSIM against currently state-of-the-art denoising algorithms, such as BM3D, BLS-GSM.

Original language	English
Pages (from-to)	1174-1178
Number of pages	5
Journal	Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology
Volume	32
Issue number	11
Publication status	Published - Nov 2012

Keywords

Circular vector
Non-local means
Rotation invariance
SAR image denoising

Cite this

@article{a28e2ab827f44ec2bd3cdb1f325cddf5,

title = "Circular-vector based non-local SAR image denoising algorithm",

abstract = "A circular-vector based non-local SAR image denoising algorithm was proposed. Circular vectors were abstracted according to the main direction of the central pixel. Feature vectors were then calculated and the weights of similarity were obtained based on these feature vectors. The execution time and quality of rotation invariance were tested. The results show that the time complexity is significantly lower than the patch-based similarity matching algorithm in NL-Means, and the rotation invariance is also maintained. Experiments have verified that the proposed algorithm shows better similarity matching results comparing to NL-Means and competitive denoising results on PSNR and SSIM against currently state-of-the-art denoising algorithms, such as BM3D, BLS-GSM.",

keywords = "Circular vector, Non-local means, Rotation invariance, SAR image denoising",

author = "Cai, \{Yu Chen\} and Zhao, \{Bao Jun\} and Tang, \{Lin Bo\}",

year = "2012",

month = nov,

language = "English",

volume = "32",

pages = "1174--1178",

journal = "Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology",

issn = "1001-0645",

publisher = "Beijing Institute of Technology",

number = "11",

}

TY - JOUR

T1 - Circular-vector based non-local SAR image denoising algorithm

AU - Cai, Yu Chen

AU - Zhao, Bao Jun

AU - Tang, Lin Bo

PY - 2012/11

Y1 - 2012/11

N2 - A circular-vector based non-local SAR image denoising algorithm was proposed. Circular vectors were abstracted according to the main direction of the central pixel. Feature vectors were then calculated and the weights of similarity were obtained based on these feature vectors. The execution time and quality of rotation invariance were tested. The results show that the time complexity is significantly lower than the patch-based similarity matching algorithm in NL-Means, and the rotation invariance is also maintained. Experiments have verified that the proposed algorithm shows better similarity matching results comparing to NL-Means and competitive denoising results on PSNR and SSIM against currently state-of-the-art denoising algorithms, such as BM3D, BLS-GSM.

AB - A circular-vector based non-local SAR image denoising algorithm was proposed. Circular vectors were abstracted according to the main direction of the central pixel. Feature vectors were then calculated and the weights of similarity were obtained based on these feature vectors. The execution time and quality of rotation invariance were tested. The results show that the time complexity is significantly lower than the patch-based similarity matching algorithm in NL-Means, and the rotation invariance is also maintained. Experiments have verified that the proposed algorithm shows better similarity matching results comparing to NL-Means and competitive denoising results on PSNR and SSIM against currently state-of-the-art denoising algorithms, such as BM3D, BLS-GSM.

KW - Circular vector

KW - Non-local means

KW - Rotation invariance

KW - SAR image denoising

UR - https://www.scopus.com/pages/publications/84871840153

M3 - Article

AN - SCOPUS:84871840153

SN - 1001-0645

VL - 32

SP - 1174

EP - 1178

JO - Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology

JF - Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology

IS - 11

ER -

Circular-vector based non-local SAR image denoising algorithm

Abstract

Keywords

Other files and links

Fingerprint

Cite this