Options
SAR Despeckling Based on CNN and Bayesian Estimator in Complex Wavelet Domain
Journal
IEEE Geoscience and Remote Sensing Letters
ISSN
1545598X
Date Issued
2022-01-01
Author(s)
Farhadiani, Ramin
Homayouni, Saeid
Bhattacharya, Avik
Mahdianpari, Masoud
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.
Subjects