SAR Despeckling Based on CNN and Bayesian Estimator in Complex Wavelet Domain
- 22 June 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 19 (1545598X) , 1-5
Abstract
We propose a hybrid algorithm for despeckling the synthetic aperture radar (SAR) images using the convolutional neural network (CNN) denoising and complex wavelet shrinkage. In particular, we perform the speckle reduction process in the complex wavelet domain. We first despeckled the approximation complex wavelet coefficients using the MUlti-channel LOgarithm with Gaussian denoising (MuLoG) algorithm based on a pretrained CNN model named fast and flexible denoising convolutional neural network (FFDNet). Next, we despeckled the log-transformed details of the complex wavelet coefficients using the averaged version of the maximum a posteriori (AMAP) estimator. The experimental results on simulated and real SAR images showed that the proposed method achieved better speckle suppression in the homogeneous areas while preserving edges and point targets than other state-of-the-art methods.Keywords
Funding Information
- Quebec Ministry of International Relations and Francophonie (124373 - MRI)
This publication has 18 references indexed in Scilit:
- FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image DenoisingIEEE Transactions on Image Processing, 2018
- Learning a Dilated Residual Network for SAR Image DespecklingRemote Sensing, 2018
- MuLoG, or How to Apply Gaussian Denoisers to Multi-Channel SAR Speckle Reduction?IEEE Transactions on Image Processing, 2017
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image DenoisingIEEE Transactions on Image Processing, 2017
- Benchmarking Framework for SAR DespecklingIEEE Transactions on Geoscience and Remote Sensing, 2013
- A Nonlocal SAR Image Denoising Algorithm Based on LLMMSE Wavelet ShrinkageIEEE Transactions on Geoscience and Remote Sensing, 2011
- SAR Image Despeckling Based on Local Homogeneous-Region Segmentation by Using Pixel-Relativity MeasurementIEEE Transactions on Geoscience and Remote Sensing, 2011
- Unsupervised Estimation of the Equivalent Number of Looks in SAR ImagesIEEE Geoscience and Remote Sensing Letters, 2011
- Speckle Noise Reduction of Medical Ultrasound Images in Complex Wavelet Domain Using Mixture PriorsIEEE Transactions on Biomedical Engineering, 2008
- Statistical properties of logarithmically transformed speckleIEEE Transactions on Geoscience and Remote Sensing, 2002