SAR Image Despeckling Based on Convolutional Denoising Autoencoder
This work offers an incremental improvement in SAR image despeckling for remote sensing and image analysis practitioners.
This paper addresses the problem of speckle noise in Synthetic Aperture Radar (SAR) images, which hinders image analysis. The authors propose a Convolutional Denoising Autoencoder (C-DAE) to reconstruct speckle-free SAR images, demonstrating improved performance over some existing methods in terms of PSNR and SSIM.
In Synthetic Aperture Radar (SAR) imaging, despeckling is very important for image analysis,whereas speckle is known as a kind of multiplicative noise caused by the coherent imaging system. During the past three decades, various algorithms have been proposed to denoise the SAR image. Generally, the BM3D is considered as the state of art technique to despeckle the speckle noise with excellent performance. More recently, deep learning make a success in image denoising and achieved a improvement over conventional method where large train dataset is required. Unlike most of the images SAR image despeckling approach, the proposed approach learns the speckle from corrupted images directly. In this paper, the limited scale of dataset make a efficient exploration by using convolutioal denoising autoencoder (C-DAE) to reconstruct the speckle-free SAR images. Batch normalization strategy is integrated with C- DAE to speed up the train time. Moreover, we compute image quality in standard metrics, PSNR and SSIM. It is revealed that our approach perform well than some others.