Underwater image enhancement using hybrid transformers and evolutionary particle swarm optimization
Abstract Underwater imaging is a complex task due to inherent challenges such as limited visibility, color distortion, and light scattering in the water medium. To address these issues and enhance underwater image quality, this research presents a novel framework based on a Hybrid Transformer Networ...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-14439-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849766267519500288 |
|---|---|
| author | Ajay Kumar Gagandeep Berar Manmohan Sharma Sakshi Ajit Noonia Gunjan Verma |
| author_facet | Ajay Kumar Gagandeep Berar Manmohan Sharma Sakshi Ajit Noonia Gunjan Verma |
| author_sort | Ajay Kumar |
| collection | DOAJ |
| description | Abstract Underwater imaging is a complex task due to inherent challenges such as limited visibility, color distortion, and light scattering in the water medium. To address these issues and enhance underwater image quality, this research presents a novel framework based on a Hybrid Transformer Network optimized using Particle Swarm Optimization (HTN-PSO). The HTN-PSO framework combines the strengths of convolutional neural networks and transformer models to effectively capture low-level features and model long-range dependencies. Simultaneously, PSO optimizes the transformer’s parameters to maximize the enhancement quality of underwater images. The proposed framework consists of four main stages: data augmentation, pre-processing, feature extraction using HTN-PSO, and enhanced image reconstruction. The performance of HTN-PSO is evaluated using objective quality metrics such as UIQM, NIQE, and BRISQUE, along with subjective assessments. The proposed model has been evaluated using HTN-PSO on four benchmark datasets: RUIE, EUVP, UWGAN, and UIEB and reports improvements over existing methods. Notably, HTN-PSO achieves a 12% increase in UIQM and up to 15% reduction in BRISQUE compared to baseline techniques, including Uformer and Restormer. Experimental results demonstrate the superiority of the HTN-PSO approach over both traditional and neural network-based methods, offering a promising avenue for improving underwater image enhancement across various domains, including exploration, research, and surveillance applications. |
| format | Article |
| id | doaj-art-ab06648c3f1d4d2c916c55eac25d69d7 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-ab06648c3f1d4d2c916c55eac25d69d72025-08-20T03:04:38ZengNature PortfolioScientific Reports2045-23222025-08-0115112110.1038/s41598-025-14439-5Underwater image enhancement using hybrid transformers and evolutionary particle swarm optimizationAjay Kumar0Gagandeep Berar1Manmohan Sharma2Sakshi3Ajit Noonia4Gunjan Verma5Department of Computer Science and Engineering, Manipal University JaipurChitkara University Institute of Engineering and Technology, Chitkara UniversityDepartment of Computer Science and Engineering, Manipal University JaipurAmity Institute of Information Technology, Amity UniversityDepartment of Computer Science and Engineering, Manipal University JaipurMaster of Computer Applications, G.L. Bajaj Institute of Technology and ManagementAbstract Underwater imaging is a complex task due to inherent challenges such as limited visibility, color distortion, and light scattering in the water medium. To address these issues and enhance underwater image quality, this research presents a novel framework based on a Hybrid Transformer Network optimized using Particle Swarm Optimization (HTN-PSO). The HTN-PSO framework combines the strengths of convolutional neural networks and transformer models to effectively capture low-level features and model long-range dependencies. Simultaneously, PSO optimizes the transformer’s parameters to maximize the enhancement quality of underwater images. The proposed framework consists of four main stages: data augmentation, pre-processing, feature extraction using HTN-PSO, and enhanced image reconstruction. The performance of HTN-PSO is evaluated using objective quality metrics such as UIQM, NIQE, and BRISQUE, along with subjective assessments. The proposed model has been evaluated using HTN-PSO on four benchmark datasets: RUIE, EUVP, UWGAN, and UIEB and reports improvements over existing methods. Notably, HTN-PSO achieves a 12% increase in UIQM and up to 15% reduction in BRISQUE compared to baseline techniques, including Uformer and Restormer. Experimental results demonstrate the superiority of the HTN-PSO approach over both traditional and neural network-based methods, offering a promising avenue for improving underwater image enhancement across various domains, including exploration, research, and surveillance applications.https://doi.org/10.1038/s41598-025-14439-5White balance (WB)Convolutional neural network (CNN)Feature extractionParticle swarm optimizationUnderwater image enhancement (UIE) |
| spellingShingle | Ajay Kumar Gagandeep Berar Manmohan Sharma Sakshi Ajit Noonia Gunjan Verma Underwater image enhancement using hybrid transformers and evolutionary particle swarm optimization Scientific Reports White balance (WB) Convolutional neural network (CNN) Feature extraction Particle swarm optimization Underwater image enhancement (UIE) |
| title | Underwater image enhancement using hybrid transformers and evolutionary particle swarm optimization |
| title_full | Underwater image enhancement using hybrid transformers and evolutionary particle swarm optimization |
| title_fullStr | Underwater image enhancement using hybrid transformers and evolutionary particle swarm optimization |
| title_full_unstemmed | Underwater image enhancement using hybrid transformers and evolutionary particle swarm optimization |
| title_short | Underwater image enhancement using hybrid transformers and evolutionary particle swarm optimization |
| title_sort | underwater image enhancement using hybrid transformers and evolutionary particle swarm optimization |
| topic | White balance (WB) Convolutional neural network (CNN) Feature extraction Particle swarm optimization Underwater image enhancement (UIE) |
| url | https://doi.org/10.1038/s41598-025-14439-5 |
| work_keys_str_mv | AT ajaykumar underwaterimageenhancementusinghybridtransformersandevolutionaryparticleswarmoptimization AT gagandeepberar underwaterimageenhancementusinghybridtransformersandevolutionaryparticleswarmoptimization AT manmohansharma underwaterimageenhancementusinghybridtransformersandevolutionaryparticleswarmoptimization AT sakshi underwaterimageenhancementusinghybridtransformersandevolutionaryparticleswarmoptimization AT ajitnoonia underwaterimageenhancementusinghybridtransformersandevolutionaryparticleswarmoptimization AT gunjanverma underwaterimageenhancementusinghybridtransformersandevolutionaryparticleswarmoptimization |