A Highly Robust Encoder–Decoder Network with Multi-Scale Feature Enhancement and Attention Gate for the Reduction of Mixed Gaussian and Salt-and-Pepper Noise in Digital Images

Image denoising is crucial for correcting distortions caused by environmental factors and technical limitations. We propose a novel and highly robust encoder–decoder network (HREDN) for effectively removing mixed salt-and-pepper and Gaussian noise from digital images. HREDN integrates a multi-scale...

Full description

Saved in:
Bibliographic Details
Main Authors: Milan Tripathi, Waree Kongprawechnon, Toshiaki Kondo
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Journal of Imaging
Subjects:
Online Access:https://www.mdpi.com/2313-433X/11/2/51
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849718452041809920
author Milan Tripathi
Waree Kongprawechnon
Toshiaki Kondo
author_facet Milan Tripathi
Waree Kongprawechnon
Toshiaki Kondo
author_sort Milan Tripathi
collection DOAJ
description Image denoising is crucial for correcting distortions caused by environmental factors and technical limitations. We propose a novel and highly robust encoder–decoder network (HREDN) for effectively removing mixed salt-and-pepper and Gaussian noise from digital images. HREDN integrates a multi-scale feature enhancement block in the encoder, allowing the network to capture features at various scales and handle complex noise patterns more effectively. To mitigate information loss during encoding, skip connections transfer essential feature maps from the encoder to the decoder, preserving structural details. However, skip connections can also propagate redundant information. To address this, we incorporate attention gates within the skip connections, ensuring that only relevant features are passed to the decoding layers. We evaluate the robustness of the proposed method across facial, medical, and remote sensing domains. The experimental results demonstrate that HREDN excels in preserving edge details and structural features in denoised images, outperforming state-of-the-art techniques in both qualitative and quantitative measures. Statistical analysis further highlights the model’s ability to effectively remove noise in diverse, complex scenarios with images of varying resolutions across multiple domains.
format Article
id doaj-art-1d80c095d07c4369b0bb02cc33c800b0
institution DOAJ
issn 2313-433X
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Journal of Imaging
spelling doaj-art-1d80c095d07c4369b0bb02cc33c800b02025-08-20T03:12:22ZengMDPI AGJournal of Imaging2313-433X2025-02-011125110.3390/jimaging11020051A Highly Robust Encoder–Decoder Network with Multi-Scale Feature Enhancement and Attention Gate for the Reduction of Mixed Gaussian and Salt-and-Pepper Noise in Digital ImagesMilan Tripathi0Waree Kongprawechnon1Toshiaki Kondo2School of Information, Computer and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, ThailandSchool of Information, Computer and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, ThailandSchool of Information, Computer and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, ThailandImage denoising is crucial for correcting distortions caused by environmental factors and technical limitations. We propose a novel and highly robust encoder–decoder network (HREDN) for effectively removing mixed salt-and-pepper and Gaussian noise from digital images. HREDN integrates a multi-scale feature enhancement block in the encoder, allowing the network to capture features at various scales and handle complex noise patterns more effectively. To mitigate information loss during encoding, skip connections transfer essential feature maps from the encoder to the decoder, preserving structural details. However, skip connections can also propagate redundant information. To address this, we incorporate attention gates within the skip connections, ensuring that only relevant features are passed to the decoding layers. We evaluate the robustness of the proposed method across facial, medical, and remote sensing domains. The experimental results demonstrate that HREDN excels in preserving edge details and structural features in denoised images, outperforming state-of-the-art techniques in both qualitative and quantitative measures. Statistical analysis further highlights the model’s ability to effectively remove noise in diverse, complex scenarios with images of varying resolutions across multiple domains.https://www.mdpi.com/2313-433X/11/2/51image denoisingGaussiansalt-and-pepperencoder–decodermulti-scale feature enhancement
spellingShingle Milan Tripathi
Waree Kongprawechnon
Toshiaki Kondo
A Highly Robust Encoder–Decoder Network with Multi-Scale Feature Enhancement and Attention Gate for the Reduction of Mixed Gaussian and Salt-and-Pepper Noise in Digital Images
Journal of Imaging
image denoising
Gaussian
salt-and-pepper
encoder–decoder
multi-scale feature enhancement
title A Highly Robust Encoder–Decoder Network with Multi-Scale Feature Enhancement and Attention Gate for the Reduction of Mixed Gaussian and Salt-and-Pepper Noise in Digital Images
title_full A Highly Robust Encoder–Decoder Network with Multi-Scale Feature Enhancement and Attention Gate for the Reduction of Mixed Gaussian and Salt-and-Pepper Noise in Digital Images
title_fullStr A Highly Robust Encoder–Decoder Network with Multi-Scale Feature Enhancement and Attention Gate for the Reduction of Mixed Gaussian and Salt-and-Pepper Noise in Digital Images
title_full_unstemmed A Highly Robust Encoder–Decoder Network with Multi-Scale Feature Enhancement and Attention Gate for the Reduction of Mixed Gaussian and Salt-and-Pepper Noise in Digital Images
title_short A Highly Robust Encoder–Decoder Network with Multi-Scale Feature Enhancement and Attention Gate for the Reduction of Mixed Gaussian and Salt-and-Pepper Noise in Digital Images
title_sort highly robust encoder decoder network with multi scale feature enhancement and attention gate for the reduction of mixed gaussian and salt and pepper noise in digital images
topic image denoising
Gaussian
salt-and-pepper
encoder–decoder
multi-scale feature enhancement
url https://www.mdpi.com/2313-433X/11/2/51
work_keys_str_mv AT milantripathi ahighlyrobustencoderdecodernetworkwithmultiscalefeatureenhancementandattentiongateforthereductionofmixedgaussianandsaltandpeppernoiseindigitalimages
AT wareekongprawechnon ahighlyrobustencoderdecodernetworkwithmultiscalefeatureenhancementandattentiongateforthereductionofmixedgaussianandsaltandpeppernoiseindigitalimages
AT toshiakikondo ahighlyrobustencoderdecodernetworkwithmultiscalefeatureenhancementandattentiongateforthereductionofmixedgaussianandsaltandpeppernoiseindigitalimages
AT milantripathi highlyrobustencoderdecodernetworkwithmultiscalefeatureenhancementandattentiongateforthereductionofmixedgaussianandsaltandpeppernoiseindigitalimages
AT wareekongprawechnon highlyrobustencoderdecodernetworkwithmultiscalefeatureenhancementandattentiongateforthereductionofmixedgaussianandsaltandpeppernoiseindigitalimages
AT toshiakikondo highlyrobustencoderdecodernetworkwithmultiscalefeatureenhancementandattentiongateforthereductionofmixedgaussianandsaltandpeppernoiseindigitalimages