A Lightweight Neural Network for Denoising Wrapped-Phase Images Generated with Full-Field Optical Interferometry
Phase wrapping is a common phenomenon in optical full-field imaging or measurement systems. It arises from large phase retardations and results in wrapped-phase maps that contain essential information about surface roughness and topology. However, these maps are often degraded by noise, such as spec...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/10/5514 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849327390519459840 |
|---|---|
| author | Muhammad Awais Younggue Kim Taeil Yoon Wonshik Choi Byeongha Lee |
| author_facet | Muhammad Awais Younggue Kim Taeil Yoon Wonshik Choi Byeongha Lee |
| author_sort | Muhammad Awais |
| collection | DOAJ |
| description | Phase wrapping is a common phenomenon in optical full-field imaging or measurement systems. It arises from large phase retardations and results in wrapped-phase maps that contain essential information about surface roughness and topology. However, these maps are often degraded by noise, such as speckle and Gaussian, which reduces the measurement accuracy and complicates phase reconstruction. Denoising such data is a fundamental problem in computer vision and plays a critical role in biomedical imaging modalities like Full-Field Optical Interferometry. In this paper, we propose WPD-Net (Wrapped-Phase Denoising Network), a lightweight deep learning-based neural network specifically designed to restore phase images corrupted by high noise levels. The network architecture integrates a shallow feature extraction module, a series of Residual Dense Attention Blocks (RDABs), and a dense feature fusion module. The RDABs incorporate attention mechanisms that help the network focus on critical features and suppress irrelevant noise, especially in high-frequency or complex regions. Additionally, WPD-Net employs a growth-rate-based feature expansion strategy to enhance multi-scale feature representation and improve phase continuity. We evaluate the model’s performance on both synthetic and experimentally acquired datasets and compare it with other state-of-the-art deep learning-based denoising methods. The results demonstrate that WPD-Net achieves superior noise suppression while preserving fine structural details even with mixed speckle and Gaussian noises. The proposed method is expected to enable fast image processing, allowing unwrapped biomedical images to be retrieved in real time. |
| format | Article |
| id | doaj-art-74c0d9d6bd414a90812a9a6cc2de7d8f |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-74c0d9d6bd414a90812a9a6cc2de7d8f2025-08-20T03:47:53ZengMDPI AGApplied Sciences2076-34172025-05-011510551410.3390/app15105514A Lightweight Neural Network for Denoising Wrapped-Phase Images Generated with Full-Field Optical InterferometryMuhammad Awais0Younggue Kim1Taeil Yoon2Wonshik Choi3Byeongha Lee4Department of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of KoreaDepartment of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of KoreaDepartment of Physics, Korea University, Seoul 02855, Republic of KoreaDepartment of Physics, Korea University, Seoul 02855, Republic of KoreaDepartment of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of KoreaPhase wrapping is a common phenomenon in optical full-field imaging or measurement systems. It arises from large phase retardations and results in wrapped-phase maps that contain essential information about surface roughness and topology. However, these maps are often degraded by noise, such as speckle and Gaussian, which reduces the measurement accuracy and complicates phase reconstruction. Denoising such data is a fundamental problem in computer vision and plays a critical role in biomedical imaging modalities like Full-Field Optical Interferometry. In this paper, we propose WPD-Net (Wrapped-Phase Denoising Network), a lightweight deep learning-based neural network specifically designed to restore phase images corrupted by high noise levels. The network architecture integrates a shallow feature extraction module, a series of Residual Dense Attention Blocks (RDABs), and a dense feature fusion module. The RDABs incorporate attention mechanisms that help the network focus on critical features and suppress irrelevant noise, especially in high-frequency or complex regions. Additionally, WPD-Net employs a growth-rate-based feature expansion strategy to enhance multi-scale feature representation and improve phase continuity. We evaluate the model’s performance on both synthetic and experimentally acquired datasets and compare it with other state-of-the-art deep learning-based denoising methods. The results demonstrate that WPD-Net achieves superior noise suppression while preserving fine structural details even with mixed speckle and Gaussian noises. The proposed method is expected to enable fast image processing, allowing unwrapped biomedical images to be retrieved in real time.https://www.mdpi.com/2076-3417/15/10/5514deep learningdenoisingdense feature fusioninterferometryresidual dense attention blockswrapped phase |
| spellingShingle | Muhammad Awais Younggue Kim Taeil Yoon Wonshik Choi Byeongha Lee A Lightweight Neural Network for Denoising Wrapped-Phase Images Generated with Full-Field Optical Interferometry Applied Sciences deep learning denoising dense feature fusion interferometry residual dense attention blocks wrapped phase |
| title | A Lightweight Neural Network for Denoising Wrapped-Phase Images Generated with Full-Field Optical Interferometry |
| title_full | A Lightweight Neural Network for Denoising Wrapped-Phase Images Generated with Full-Field Optical Interferometry |
| title_fullStr | A Lightweight Neural Network for Denoising Wrapped-Phase Images Generated with Full-Field Optical Interferometry |
| title_full_unstemmed | A Lightweight Neural Network for Denoising Wrapped-Phase Images Generated with Full-Field Optical Interferometry |
| title_short | A Lightweight Neural Network for Denoising Wrapped-Phase Images Generated with Full-Field Optical Interferometry |
| title_sort | lightweight neural network for denoising wrapped phase images generated with full field optical interferometry |
| topic | deep learning denoising dense feature fusion interferometry residual dense attention blocks wrapped phase |
| url | https://www.mdpi.com/2076-3417/15/10/5514 |
| work_keys_str_mv | AT muhammadawais alightweightneuralnetworkfordenoisingwrappedphaseimagesgeneratedwithfullfieldopticalinterferometry AT youngguekim alightweightneuralnetworkfordenoisingwrappedphaseimagesgeneratedwithfullfieldopticalinterferometry AT taeilyoon alightweightneuralnetworkfordenoisingwrappedphaseimagesgeneratedwithfullfieldopticalinterferometry AT wonshikchoi alightweightneuralnetworkfordenoisingwrappedphaseimagesgeneratedwithfullfieldopticalinterferometry AT byeonghalee alightweightneuralnetworkfordenoisingwrappedphaseimagesgeneratedwithfullfieldopticalinterferometry AT muhammadawais lightweightneuralnetworkfordenoisingwrappedphaseimagesgeneratedwithfullfieldopticalinterferometry AT youngguekim lightweightneuralnetworkfordenoisingwrappedphaseimagesgeneratedwithfullfieldopticalinterferometry AT taeilyoon lightweightneuralnetworkfordenoisingwrappedphaseimagesgeneratedwithfullfieldopticalinterferometry AT wonshikchoi lightweightneuralnetworkfordenoisingwrappedphaseimagesgeneratedwithfullfieldopticalinterferometry AT byeonghalee lightweightneuralnetworkfordenoisingwrappedphaseimagesgeneratedwithfullfieldopticalinterferometry |