A deep neural network learning‐based speckle noise removal technique for enhancing the quality of synthetic‐aperture radar images

Abstract

The speckle noise present in synthetic‐aperture radar (SAR) images is responsible for hindering the extraction of the exact information that needs to be utilized for potential remote sensing applications. Thus the quality of SAR images needs to be enhanced by removing speckle noise in an effective manner. In this paper, A Deep Neural Network‐based Speckle Noise Removal Technique (DNN‐SNRT) is proposed that utilizes the benefits of convolution and Long Short Term Memory‐based neural networks to enhance the quality of SAR images. The proposed DNN‐SNRT uses multiple radar intensity images that are archived from the specific area of interest to facilitate the self‐learning of the intensity features derived from the image patches. The proposed DNN‐SNRT incorporates a dual neural network to remove speckle noise and flexibly estimates the thresholds and weights to achieve an effective SAR image quality improvement. The proposed DNN‐SNRT is capable of automatically updating the intensity features of SAR images during the training process. Experimental investigation of the proposed DNN‐SNRT conducted based on TerraSAR‐X images confirmed the superior enhancement of image quality over comparable recent filters. The results of the DNN‐SNRT scheme were also proved that it is able to reduce noise and preserve edges during the image quality enhancement process.

HELIOS: High-speed sequence alignment in optics

“…It also affects the performance of automatic analysis methods intended for objective and accurate quantifications. Although the resolution, speed, and depth of optical imaging systems have been greatly enhanced recently [ 79 , 80 ], their intrinsic problem (i.e. speckle noise) has not been completely solved.…”

Two‐step morphology‐based denoising and non‐local means smoothing improves micro‐computed tomography digital rock images

“…In order to quantify how well the homogeneous regions of the image are denoised, we used the ENL metric, which has been widely used in the literature (Shamsoddini et al., 2010; Gong et al., 2015; X. Wang et al., 2012; Mohan et al., 2021) in the context of speckle noise removal. Mathematically, the ENL is defined as below: $$$$\begin{equation} \text{ENL}_{\rm ROI} = \frac{\mu _{\rm ROI}^2}{\sigma _{\rm ROI}^2}, \end{equation}$$$$…”

Feature Pyramid U-Net with Attention for Semantic Segmentation of Forward-Looking Sonar Images

“…This interference can result in blurred target areas and complex edge information, which seriously affect subsequent image processing [ 12 ]. Despite the existence of synthetic aperture sonar, which can provide high-resolution sonar images and is nearly independent of frequency and target range [ 13 , 14 ], it still has speckle noise in its images [ 15 ], which does not facilitate us to develop further studies of the images.…”

“…These methods have disadvantages of high algorithm complexity, slow recognition speed, and high image quality requirements [ 15 , 30 , 31 , 32 ], so there is an urgent need for more efficient sonar image segmentation methods. Neural-network-based image segmentation has become a popular research direction [ 33 ] as it has excellent performance in complex image segmentation.…”