Speckle Noise Suppression in Digital Images Utilizing Deep Refinement Network
This paper proposes a deep learning model for speckle noise suppression in digital images. The model consists of two interconnected networks: the first network focuses on the initial suppression of speckle noise. The second network refines these features, capturing more complex patterns, and preser...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Brno University of Technology
2024-06-01
|
| Series: | Mendel |
| Subjects: | |
| Online Access: | https://mendel-journal.org/index.php/mendel/article/view/301 |
| _version_ | 1827354007024173056 |
|---|---|
| author | Mohamed AbdelNasser Ehab Alaa Saleh Mostafa I. Soliman |
| author_facet | Mohamed AbdelNasser Ehab Alaa Saleh Mostafa I. Soliman |
| author_sort | Mohamed AbdelNasser |
| collection | DOAJ |
| description |
This paper proposes a deep learning model for speckle noise suppression in digital images. The model consists of two interconnected networks: the first network focuses on the initial suppression of speckle noise. The second network refines these features, capturing more complex patterns, and preserving the texture details of the input images. The performance of the proposed model is evaluated with different backbones for the two networks: ResNet-18, ResNet-50, and SENet-154. Experimental results on two datasets, the Boss steganography, and COVIDx CXR-3, demonstrate that the proposed method yields competitive despeckling results. The proposed model with the SENet-154 encoder achieves PSNR and SNR values higher than 37 dB with the two datasets and outperforms other state-of-the-art methods (Pixel2Pixel, DiscoGAN, and BicycleGAN).
|
| first_indexed | 2024-03-08T03:39:26Z |
| format | Article |
| id | doaj.art-c318e11b08054d7ea3845f288ea2e864 |
| institution | Directory Open Access Journal |
| issn | 1803-3814 2571-3701 |
| language | English |
| last_indexed | 2024-03-08T03:39:26Z |
| publishDate | 2024-06-01 |
| publisher | Brno University of Technology |
| record_format | Article |
| series | Mendel |
| spelling | doaj.art-c318e11b08054d7ea3845f288ea2e8642024-02-09T23:24:03ZengBrno University of TechnologyMendel1803-38142571-37012024-06-0130110.13164/mendel.2024.1.015Speckle Noise Suppression in Digital Images Utilizing Deep Refinement NetworkMohamed AbdelNasser0Ehab Alaa Saleh1Mostafa I. Soliman2Aswan UniversityAswan UniversityEgypt-Japan University of Science and Technology This paper proposes a deep learning model for speckle noise suppression in digital images. The model consists of two interconnected networks: the first network focuses on the initial suppression of speckle noise. The second network refines these features, capturing more complex patterns, and preserving the texture details of the input images. The performance of the proposed model is evaluated with different backbones for the two networks: ResNet-18, ResNet-50, and SENet-154. Experimental results on two datasets, the Boss steganography, and COVIDx CXR-3, demonstrate that the proposed method yields competitive despeckling results. The proposed model with the SENet-154 encoder achieves PSNR and SNR values higher than 37 dB with the two datasets and outperforms other state-of-the-art methods (Pixel2Pixel, DiscoGAN, and BicycleGAN). https://mendel-journal.org/index.php/mendel/article/view/301Speckle NoiseImage FilteringImage DespeckingDenoisingImage EnhancementDeep Learning |
| spellingShingle | Mohamed AbdelNasser Ehab Alaa Saleh Mostafa I. Soliman Speckle Noise Suppression in Digital Images Utilizing Deep Refinement Network Mendel Speckle Noise Image Filtering Image Despecking Denoising Image Enhancement Deep Learning |
| title | Speckle Noise Suppression in Digital Images Utilizing Deep Refinement Network |
| title_full | Speckle Noise Suppression in Digital Images Utilizing Deep Refinement Network |
| title_fullStr | Speckle Noise Suppression in Digital Images Utilizing Deep Refinement Network |
| title_full_unstemmed | Speckle Noise Suppression in Digital Images Utilizing Deep Refinement Network |
| title_short | Speckle Noise Suppression in Digital Images Utilizing Deep Refinement Network |
| title_sort | speckle noise suppression in digital images utilizing deep refinement network |
| topic | Speckle Noise Image Filtering Image Despecking Denoising Image Enhancement Deep Learning |
| url | https://mendel-journal.org/index.php/mendel/article/view/301 |
| work_keys_str_mv | AT mohamedabdelnasser specklenoisesuppressionindigitalimagesutilizingdeeprefinementnetwork AT ehabalaasaleh specklenoisesuppressionindigitalimagesutilizingdeeprefinementnetwork AT mostafaisoliman specklenoisesuppressionindigitalimagesutilizingdeeprefinementnetwork |