Comparison of neural networks for suppression of multiplicative noise in images
The paper compares several neural network (NN) architectures for suppression of multiplicative noise. The images may contain sharp boundaries and large homogeneous areas. Convolutional and fully connected networks are investigated. It is shown that different architectures require significantly diffe...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Samara National Research University
2024-06-01
|
| Series: | Компьютерная оптика |
| Subjects: | |
| Online Access: | https://www.computeroptics.ru/eng/KO/Annot/KO48-3/480313e.html |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832086519976820736 |
|---|---|
| author | V.A. Pavlov A.A. Belov V.T. Nguen N. Jovanovski A.S. Ovsyannikova |
| author_facet | V.A. Pavlov A.A. Belov V.T. Nguen N. Jovanovski A.S. Ovsyannikova |
| author_sort | V.A. Pavlov |
| collection | DOAJ |
| description | The paper compares several neural network (NN) architectures for suppression of multiplicative noise. The images may contain sharp boundaries and large homogeneous areas. Convolutional and fully connected networks are investigated. It is shown that different architectures require significantly different amount of training data to reach the same noise suppression quality. Examples of NN requiring lower amounts of training data are presented. |
| format | Article |
| id | doaj-art-8ddcd6bb50b1491b97a00ab9d2c1e56b |
| institution | Kabale University |
| issn | 0134-2452 2412-6179 |
| language | English |
| publishDate | 2024-06-01 |
| publisher | Samara National Research University |
| record_format | Article |
| series | Компьютерная оптика |
| spelling | doaj-art-8ddcd6bb50b1491b97a00ab9d2c1e56b2025-02-06T12:25:17ZengSamara National Research UniversityКомпьютерная оптика0134-24522412-61792024-06-0148342543110.18287/2412-6179-CO-1400Comparison of neural networks for suppression of multiplicative noise in imagesV.A. Pavlov0A.A. Belov1V.T. Nguen2N. Jovanovski3 A.S. Ovsyannikova4Peter the Great St. Petersburg Polytechnic UniversityPeter the Great St. Petersburg Polytechnic UniversityPeter the Great St. Petersburg Polytechnic UniversityPeter the Great St. Petersburg Polytechnic UniversityPeter the Great St. Petersburg Polytechnic UniversityThe paper compares several neural network (NN) architectures for suppression of multiplicative noise. The images may contain sharp boundaries and large homogeneous areas. Convolutional and fully connected networks are investigated. It is shown that different architectures require significantly different amount of training data to reach the same noise suppression quality. Examples of NN requiring lower amounts of training data are presented.https://www.computeroptics.ru/eng/KO/Annot/KO48-3/480313e.htmlspeckle noiseradar imagesarnoise reductionimage processingneural network |
| spellingShingle | V.A. Pavlov A.A. Belov V.T. Nguen N. Jovanovski A.S. Ovsyannikova Comparison of neural networks for suppression of multiplicative noise in images Компьютерная оптика speckle noise radar image sar noise reduction image processing neural network |
| title | Comparison of neural networks for suppression of multiplicative noise in images |
| title_full | Comparison of neural networks for suppression of multiplicative noise in images |
| title_fullStr | Comparison of neural networks for suppression of multiplicative noise in images |
| title_full_unstemmed | Comparison of neural networks for suppression of multiplicative noise in images |
| title_short | Comparison of neural networks for suppression of multiplicative noise in images |
| title_sort | comparison of neural networks for suppression of multiplicative noise in images |
| topic | speckle noise radar image sar noise reduction image processing neural network |
| url | https://www.computeroptics.ru/eng/KO/Annot/KO48-3/480313e.html |
| work_keys_str_mv | AT vapavlov comparisonofneuralnetworksforsuppressionofmultiplicativenoiseinimages AT aabelov comparisonofneuralnetworksforsuppressionofmultiplicativenoiseinimages AT vtnguen comparisonofneuralnetworksforsuppressionofmultiplicativenoiseinimages AT njovanovski comparisonofneuralnetworksforsuppressionofmultiplicativenoiseinimages AT asovsyannikova comparisonofneuralnetworksforsuppressionofmultiplicativenoiseinimages |