SID-TGAN: A Transformer-Based Generative Adversarial Network for Sonar Image Despeckling
Open Access
- 23 October 2023
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 15 (20) , 5072
Abstract
Sonar images are inherently affected by speckle noise, which degrades image quality and hinders image exploitation. Despeckling is an important pre-processing task that aims to remove such noise so as to improve the accuracy of analysis tasks on sonar images. In this paper, we propose a novel transformer-based generative adversarial network named SID-TGAN for sonar image despeckling. In the SID-TGAN framework, transformer and convolutional blocks are used to extract global and local features, which are further integrated into the generator and discriminator networks for feature fusion and enhancement. By leveraging adversarial training, SID-TGAN learns more comprehensive representations of sonar images and shows outstanding performance in speckle denoising. Meanwhile, SID-TGAN introduces a new adversarial loss function that combines image content, local texture style, and global similarity to reduce image distortion and information loss during training. Finally, we compare SID-TGAN with state-of-the-art despeckling methods on one image dataset with synthetic optical noise and four real sonar image datasets. The results show that it achieves significantly better despeckling performance than existing methods on all five datasets.Keywords
Funding Information
- National Natural Science Foundation of China (61976032, 62002039)
This publication has 27 references indexed in Scilit:
- Dilated convolution neural network with LeakyReLU for environmental sound classification2017
- SAR image despeckling through convolutional neural networks2017
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Denoising auto-encoder based image enhancement for high resolution sonar image2017
- A Robust and Fast Method for Sidescan Sonar Image Segmentation Using Nonlocal Despeckling and Active Contour ModelIEEE Transactions on Cybernetics, 2016
- Fast R-CNN2015
- A Method for Sonar Image Segmentation Based on Combination of MRF and Region Growing2015
- BM3D Frames and Variational Image DeblurringIEEE Transactions on Image Processing, 2011
- Iterative Weighted Maximum Likelihood Denoising With Probabilistic Patch-Based WeightsIEEE Transactions on Image Processing, 2009
- Speckle noise reduction in SAS imagerySignal Processing, 2007