Publication
Title
SAR image denoising using homomorphic and shearlet transforms
Author
Abstract
Recently, denoising of Synthetic Aperture Radar (SAR) images has gained particular attention. SAR image is usually affected by speckle noise. In this paper a new method for speckle noise reduction of SAR images using shearlet transform (ST) is introduced. ST could significantly remove the Gaussian noise therefore in the proposed method first, noisy images are converted to a domain which type of noise is Gaussian using homomorphic transform (HT). Second, 2D shearlet is applied to the data. Third, the hard thresholding is used in order to denoise the shearlet coefficients. Finally reconstructed denoised images are obtained by applying the inverse shearlet and homomorphic transforms. The proposed method (ST-HT) is compared with state of art denoising algorithms on SAR images. Obtained results show the superiority of the proposed approach.
Language
English
Source (journal)
2017 3RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION AND IMAGE ANALYSIS (IPRIA)
Source (book)
3rd International Conference on Pattern Analysis and Image Analysis, (IPRIA), APR 19-20, 2017, Shahrekord Univ, Faculty Technol & Eng, Shahrekord Univ, Faculty Technol & Eng, Shahrekord, IRAN
Publication
New york : Ieee , 2017
ISBN
978-1-5090-6454-0
978-1-5090-6454-0
Volume/pages
(2017) , p. 80-83
ISI
000426933500014
Full text (Publisher's DOI)
Full text (publisher's version - intranet only)
UAntwerpen
Faculty/Department
Research group
Publication type
Subject
Affiliation
Publications with a UAntwerp address
External links
Web of Science
Record
Identification
Creation 29.03.2018
Last edited 16.09.2021
To cite this reference