Neural shrinkage for wavelet-based SAR despeckling

2016/07/31 by Mastriani, Mario, Giraldez, Alberto E.
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1608.00279

Abstract

The wavelet shrinkage denoising approach is able to maintain local regularity of a signal while suppressing noise. However, the conventional wavelet shrinkage based methods are not time-scale adaptive to track the local time-scale variation. In this paper, a new type of Neural Shrinkage (NS) is presented with a new class of shrinkage architecture for speckle reduction in Synthetic Aperture Radar (SAR) images. The numerical results indicate that the new method outperforms the standard filters, the standard wavelet shrinkage despeckling method, and previous NS.

Related

• Towards Frequency-Adaptive Learning for SAR Despeckling
• NeighCNN: A CNN based SAR Speckle Reduction using Feature preserving Loss Function
• New wavelet-based superresolution algorithm for speckle reduction in SAR images
• Kalman's shrinkage for wavelet-based despeckling of SAR images
• SAR image despeckling through convolutional neural networks