Advancements in Efficient Underwater Image Restoration Using ETransMapNet for Enhanced Dehazing
Underwater (UW) information is essential for advancing human exploration and utilization of the underwater world, including fields such as UW Paleology, UW Target Detection, UW Object Tracking, UW Surveillance, and related activities. Visual media like movies and images enhance our natural understan...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek
2025-01-01
|
| Series: | Tehnički Vjesnik |
| Subjects: | |
| Online Access: | https://hrcak.srce.hr/file/478040 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849323054598979584 |
|---|---|
| author | C. P. Indumathi Haya Mesfer Alshahrani N. A. Natraj C. H. Sarada Devi |
| author_facet | C. P. Indumathi Haya Mesfer Alshahrani N. A. Natraj C. H. Sarada Devi |
| author_sort | C. P. Indumathi |
| collection | DOAJ |
| description | Underwater (UW) information is essential for advancing human exploration and utilization of the underwater world, including fields such as UW Paleology, UW Target Detection, UW Object Tracking, UW Surveillance, and related activities. Visual media like movies and images enhance our natural understanding of underwater objectives. In the past decade, underwater photo restoration and enhancement have gained increasing attention. This study proposes a novel approach employing the recently developed Convolutional Neural Network (CNN) for dehazing, named ETransMapNet (Efficient Transmission Map Network). ETransMapNet is designed with convolution layers and nonlinear activations to execute four sequential processes: nonlinear regression, local maxima detection, multi-scale decomposition, and convolutional feature extraction. Unlike traditional CNNs, ETransMapNet replaces the initial layer's Rectified Linear Unit (ReLU) activation with a convolution layer utilizing a Maxout activation function. ETransMapNet extracts features using three convolution kernels of different sizes (3 × 3, 5 × 5, and 7 × 7). The method suppresses noise in the estimated transmittance map, while local extremum values maintain local consistency within the transmittance map. This study adopts Bilateral ReLU (BReLU) for normalizing network outputs within a 0 to 1 range. Additionally, Adaptive Bilateral Filtering (ABF) is applied to remove redundant artifacts from the predicted transmission map. White balancing addresses color divergence, and Laplacian pyramid fusion combines the color-corrected and dehazed images. In the final stage, the resultant image is transformed into the Wavelet and Directional Filter Banks (WDFB) domain for denoising and edge enhancement. Performance metrics reveal that the proposed ETransMapNet approach improves performance by 38% - 50% compared to previous methods. |
| format | Article |
| id | doaj-art-29edea22fda64cdd89b5b8d3f5ebf9e1 |
| institution | Kabale University |
| issn | 1330-3651 1848-6339 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek |
| record_format | Article |
| series | Tehnički Vjesnik |
| spelling | doaj-art-29edea22fda64cdd89b5b8d3f5ebf9e12025-08-20T03:49:12ZengFaculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in OsijekTehnički Vjesnik1330-36511848-63392025-01-013231125113210.17559/TV-20240508001530Advancements in Efficient Underwater Image Restoration Using ETransMapNet for Enhanced DehazingC. P. Indumathi0Haya Mesfer Alshahrani1N. A. Natraj2C. H. Sarada Devi3Department of Computer Science and Engineering, University College of Engineering, BIT Campus, Anna University Tiruchirapalli-24, Tamilnadu, IndiaDepartment of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi ArabiaSymbiosis Institute of Digital and Telecom Management, Symbiosis International (Deemed University), Pune, Maharashtra, IndiaDepartment of CSE Meenakshi College of Engineering, IndiaUnderwater (UW) information is essential for advancing human exploration and utilization of the underwater world, including fields such as UW Paleology, UW Target Detection, UW Object Tracking, UW Surveillance, and related activities. Visual media like movies and images enhance our natural understanding of underwater objectives. In the past decade, underwater photo restoration and enhancement have gained increasing attention. This study proposes a novel approach employing the recently developed Convolutional Neural Network (CNN) for dehazing, named ETransMapNet (Efficient Transmission Map Network). ETransMapNet is designed with convolution layers and nonlinear activations to execute four sequential processes: nonlinear regression, local maxima detection, multi-scale decomposition, and convolutional feature extraction. Unlike traditional CNNs, ETransMapNet replaces the initial layer's Rectified Linear Unit (ReLU) activation with a convolution layer utilizing a Maxout activation function. ETransMapNet extracts features using three convolution kernels of different sizes (3 × 3, 5 × 5, and 7 × 7). The method suppresses noise in the estimated transmittance map, while local extremum values maintain local consistency within the transmittance map. This study adopts Bilateral ReLU (BReLU) for normalizing network outputs within a 0 to 1 range. Additionally, Adaptive Bilateral Filtering (ABF) is applied to remove redundant artifacts from the predicted transmission map. White balancing addresses color divergence, and Laplacian pyramid fusion combines the color-corrected and dehazed images. In the final stage, the resultant image is transformed into the Wavelet and Directional Filter Banks (WDFB) domain for denoising and edge enhancement. Performance metrics reveal that the proposed ETransMapNet approach improves performance by 38% - 50% compared to previous methods.https://hrcak.srce.hr/file/478040Adaptive Bilateral Filtering (ABF)Convolutional Neural Network (CNN)ETransMapNettransmission map denoisingunderwater image restoration |
| spellingShingle | C. P. Indumathi Haya Mesfer Alshahrani N. A. Natraj C. H. Sarada Devi Advancements in Efficient Underwater Image Restoration Using ETransMapNet for Enhanced Dehazing Tehnički Vjesnik Adaptive Bilateral Filtering (ABF) Convolutional Neural Network (CNN) ETransMapNet transmission map denoising underwater image restoration |
| title | Advancements in Efficient Underwater Image Restoration Using ETransMapNet for Enhanced Dehazing |
| title_full | Advancements in Efficient Underwater Image Restoration Using ETransMapNet for Enhanced Dehazing |
| title_fullStr | Advancements in Efficient Underwater Image Restoration Using ETransMapNet for Enhanced Dehazing |
| title_full_unstemmed | Advancements in Efficient Underwater Image Restoration Using ETransMapNet for Enhanced Dehazing |
| title_short | Advancements in Efficient Underwater Image Restoration Using ETransMapNet for Enhanced Dehazing |
| title_sort | advancements in efficient underwater image restoration using etransmapnet for enhanced dehazing |
| topic | Adaptive Bilateral Filtering (ABF) Convolutional Neural Network (CNN) ETransMapNet transmission map denoising underwater image restoration |
| url | https://hrcak.srce.hr/file/478040 |
| work_keys_str_mv | AT cpindumathi advancementsinefficientunderwaterimagerestorationusingetransmapnetforenhanceddehazing AT hayamesferalshahrani advancementsinefficientunderwaterimagerestorationusingetransmapnetforenhanceddehazing AT nanatraj advancementsinefficientunderwaterimagerestorationusingetransmapnetforenhanceddehazing AT chsaradadevi advancementsinefficientunderwaterimagerestorationusingetransmapnetforenhanceddehazing |