Zooming Into Clarity: Image Denoising Through Innovative Autoencoder Architectures
<p dir="ltr">In today’s era of increasing data complexity and pervasive noise, robust techniques for data processing, reconstruction, and denoising are crucial. Autoencoders, known for their adaptability in unsupervised learning, offer a strategic solution to these challenges. This r...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , |
| منشور في: |
2024
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1864513541475663872 |
|---|---|
| author | Khatereh Mohammadi (17309662) |
| author2 | Ashhadul Islam (16869981) Samir Brahim Belhaouari (9427347) |
| author2_role | author author |
| author_facet | Khatereh Mohammadi (17309662) Ashhadul Islam (16869981) Samir Brahim Belhaouari (9427347) |
| author_role | author |
| dc.creator.none.fl_str_mv | Khatereh Mohammadi (17309662) Ashhadul Islam (16869981) Samir Brahim Belhaouari (9427347) |
| dc.date.none.fl_str_mv | 2024-07-24T03:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1109/access.2024.3424972 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/Zooming_Into_Clarity_Image_Denoising_Through_Innovative_Autoencoder_Architectures/29900276 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Information and computing sciences Artificial intelligence Computer vision and multimedia computation Machine learning Autoencoders data reconstruction noise reduction loss function architecture high-resolution imaging enhancement Noise reduction Image reconstruction Convolutional codes Feature extraction Task analysis Image enhancement |
| dc.title.none.fl_str_mv | Zooming Into Clarity: Image Denoising Through Innovative Autoencoder Architectures |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p dir="ltr">In today’s era of increasing data complexity and pervasive noise, robust techniques for data processing, reconstruction, and denoising are crucial. Autoencoders, known for their adaptability in unsupervised learning, offer a strategic solution to these challenges. This research introduces two novel autoencoder architectures, ResoFocus and FragmentumZoom, complemented by a refined loss function. The ResoFocus Autoencoder is designed to optimize and denoise upsized images, while the FragmentumZoom Autoencoder targets small image segments to enhance denoising tasks. Empirical evaluations on diverse datasets, including CelebA and Autism Face data, demonstrate significant improvements in the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM). For the CelebA dataset, the ResoFocus 4X autoencoder achieved PSNR values of 31.578, with a peak increase of 1.9 dB compared to the baseline Simple autoencoder and SSIM values of 0.898 at 1000 epochs. In the Autism Face dataset, the FragmentumZoom 4X autoencoder recorded PSNR values of 30.951, with an increase of 1.289 dB over the baseline, and SSIM values of 0.906. These results underscore the efficacy of these novel architectures in improving image quality and advancing image processing techniques, particularly in scenarios requiring heightened resolution and noise reduction.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2024.3424972" target="_blank">https://dx.doi.org/10.1109/access.2024.3424972</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_513b4cbac9a62307b4996490ae91d051 |
| identifier_str_mv | 10.1109/access.2024.3424972 |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/29900276 |
| publishDate | 2024 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Zooming Into Clarity: Image Denoising Through Innovative Autoencoder ArchitecturesKhatereh Mohammadi (17309662)Ashhadul Islam (16869981)Samir Brahim Belhaouari (9427347)Information and computing sciencesArtificial intelligenceComputer vision and multimedia computationMachine learningAutoencodersdata reconstructionnoise reductionloss functionarchitecturehigh-resolution imaging enhancementNoise reductionImage reconstructionConvolutional codesFeature extractionTask analysisImage enhancement<p dir="ltr">In today’s era of increasing data complexity and pervasive noise, robust techniques for data processing, reconstruction, and denoising are crucial. Autoencoders, known for their adaptability in unsupervised learning, offer a strategic solution to these challenges. This research introduces two novel autoencoder architectures, ResoFocus and FragmentumZoom, complemented by a refined loss function. The ResoFocus Autoencoder is designed to optimize and denoise upsized images, while the FragmentumZoom Autoencoder targets small image segments to enhance denoising tasks. Empirical evaluations on diverse datasets, including CelebA and Autism Face data, demonstrate significant improvements in the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM). For the CelebA dataset, the ResoFocus 4X autoencoder achieved PSNR values of 31.578, with a peak increase of 1.9 dB compared to the baseline Simple autoencoder and SSIM values of 0.898 at 1000 epochs. In the Autism Face dataset, the FragmentumZoom 4X autoencoder recorded PSNR values of 30.951, with an increase of 1.289 dB over the baseline, and SSIM values of 0.906. These results underscore the efficacy of these novel architectures in improving image quality and advancing image processing techniques, particularly in scenarios requiring heightened resolution and noise reduction.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2024.3424972" target="_blank">https://dx.doi.org/10.1109/access.2024.3424972</a></p>2024-07-24T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2024.3424972https://figshare.com/articles/journal_contribution/Zooming_Into_Clarity_Image_Denoising_Through_Innovative_Autoencoder_Architectures/29900276CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/299002762024-07-24T03:00:00Z |
| spellingShingle | Zooming Into Clarity: Image Denoising Through Innovative Autoencoder Architectures Khatereh Mohammadi (17309662) Information and computing sciences Artificial intelligence Computer vision and multimedia computation Machine learning Autoencoders data reconstruction noise reduction loss function architecture high-resolution imaging enhancement Noise reduction Image reconstruction Convolutional codes Feature extraction Task analysis Image enhancement |
| status_str | publishedVersion |
| title | Zooming Into Clarity: Image Denoising Through Innovative Autoencoder Architectures |
| title_full | Zooming Into Clarity: Image Denoising Through Innovative Autoencoder Architectures |
| title_fullStr | Zooming Into Clarity: Image Denoising Through Innovative Autoencoder Architectures |
| title_full_unstemmed | Zooming Into Clarity: Image Denoising Through Innovative Autoencoder Architectures |
| title_short | Zooming Into Clarity: Image Denoising Through Innovative Autoencoder Architectures |
| title_sort | Zooming Into Clarity: Image Denoising Through Innovative Autoencoder Architectures |
| topic | Information and computing sciences Artificial intelligence Computer vision and multimedia computation Machine learning Autoencoders data reconstruction noise reduction loss function architecture high-resolution imaging enhancement Noise reduction Image reconstruction Convolutional codes Feature extraction Task analysis Image enhancement |