Neuro-Fuzzy Approach for Speckle Noise Reduction in SAR Images

Singanamalla, Vijayakumar; Vaithyanathan, Santhi

doi:10.1007/978-981-10-4859-3_23

Cited by 5 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The total variation loss and Euclidean loss factors are used by the Convolutional Neural Networks to ascertain peak image quality with edge preservation. A Type 2‐based Neuro Fuzzy Scheme (Type‐2‐NFS) for suppressing speckle noise was developed to ensure effective non local filtering processes 17 . The Type‐2‐NFS incorporated the benefits of primitive networking and adjacency relations to suppress speckle noise in SAR images.…”

Section: Related Workmentioning

confidence: 99%

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

Mohan¹,

Arunachalam

Sunitha³

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

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

Mohan¹,

Arunachalam

Sunitha³

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Our work has high potential in manipulating the time series of SAR images of various landscapes and terrains as, for example, SAR images of ocean beds [5]. The proposed neural approach also tends to develop higher traceability of SAR images despite speckle noise [6], which is directly proportional to pixel intensities. This neural architecture can be applied with computational intelligence (Neuro-Fuzzy Logic System) [7] that includes preserving edges and texture information [7].…”

Section: Related Workmentioning

confidence: 99%

A Deep Neural Approach Toward Staining and Tinting of Monochrome Images

Neogi

Das

Deb

2021

Advanced Computing and Intelligent Technologies

View full text Add to dashboard Cite

The paper presents a system that colorizes monochrome images driven by deep neural networks without any additional supportive aid. Throughout the paper, we explore feature engineering, transfer learning, color spaces and color channels, and various architectural neural frameworks. Eventually, stained and tinted colorized images or image sequences (video) have been derived from monochrome images that are more aesthetically pleasing, information rich, and more vivid with higher traceability. The experimental results illustrae the viability of our methodology and divulge a favorable route for future work.

show abstract