{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T04:34:04Z","timestamp":1780634044211,"version":"3.54.1"},"reference-count":57,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100012363","name":"Saudi Arabia Cultural Bureau in London","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012363","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>This paper provides an exploratory analysis of underwater video analysis techniques to enhance image quality and facilitate accurate classification of different marine species. Our methodology progresses through several steps, beginning with the quality of underwater images that might be reduced by variables such as decreased light intensity, color modification, and limited visibility. These attributes pose significant challenges to develop accurate object detection methods. This paper outlines the processing pipeline employed to enhance the quality of images from underwater videos and facilitate precise object detection. First, we use the Gray World (GW) algorithm for image enhancement, effectively mitigating the challenges of aquatic environment, such as color distortion and low contrast. Subsequently, we compare the traditional Histogram Equalization (HE) and the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithms to assess their efficacy in enhancing underwater image quality. Next, Canny Edge Detection is utilized to identify the prominent features in the enhanced images, aiding in subsequent classification tasks. Next, three state-of-the-art deep learning models, Visual Geometry Group 16-layer network (VGG16), 50-layer Residual Network (ResNet50), and 121-layer Densely Connected Convolutional Network (DenseNet121), are leveraged through transfer learning to classify underwater species, including fish, coral reefs, and sea turtles. Finally, by enhancing the visual quality of underwater images, our research contributes to better understanding of the underwater ecosystem and supports conservation efforts. Enhanced Super-Resolution GAN (ESRGAN) is a superior Generative Adversarial Network (GAN) technique to improve the quality of noisy images. This paper contributes to advancing the field of underwater image and video analysis, offering valuable insights for applications in marine biology, environmental monitoring, underwater robotics, and autonomous navigation.<\/jats:p>","DOI":"10.1371\/journal.pone.0345593","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:56:58Z","timestamp":1774634218000},"page":"e0345593","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["GAN-based underwater image enhancement and scene classification using transfer learning"],"prefix":"10.1371","volume":"21","author":[{"given":"Amani","family":"Homoud","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8394-5303","authenticated-orcid":true,"given":"Saptarshi","family":"Das","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,3,27]]},"reference":[{"key":"pone.0345593.ref001","first-page":"1","volume-title":"Vision based real-time fish detection using convolutional neural network. In: OCEANS 2017","author":"M Sung","year":"2017"},{"issue":"3","key":"pone.0345593.ref002","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1111\/1365-2656.12780","article-title":"A computer vision for animal ecology","volume":"87","author":"BG Weinstein","year":"2018","journal-title":"J Anim Ecol"},{"issue":"1","key":"pone.0345593.ref003","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1093\/icesjms\/fsx109","article-title":"Automatic fish species classification in underwater videos: exploiting pre-trained deep neural network models to compensate for limited labelled data","volume":"75","author":"SA Siddiqui","year":"2017","journal-title":"ICES Journal of Marine Science"},{"key":"pone.0345593.ref004","doi-asserted-by":"crossref","DOI":"10.3389\/fmars.2020.00429","article-title":"Automating the Analysis of Fish Abundance Using Object Detection: Optimizing Animal Ecology With Deep Learning","volume":"7","author":"EM Ditria","year":"2020","journal-title":"Front Mar Sci"},{"key":"pone.0345593.ref005","doi-asserted-by":"crossref","unstructured":"Tamou AB, Benzinou A, Nasreddine K, Ballihi L. Transfer Learning with deep Convolutional Neural Network for Underwater Live Fish Recognition. In: 2018 IEEE International Conference on Image Processing, Applications and Systems (IPAS), 2018. 204\u20139. https:\/\/doi.org\/10.1109\/ipas.2018.8708871","DOI":"10.1109\/IPAS.2018.8708871"},{"key":"pone.0345593.ref006","doi-asserted-by":"crossref","first-page":"101088","DOI":"10.1016\/j.ecoinf.2020.101088","article-title":"Fish detection and species classification in underwater environments using deep learning with temporal information","volume":"57","author":"A Jalal","year":"2020","journal-title":"Ecological Informatics"},{"key":"pone.0345593.ref007","doi-asserted-by":"crossref","unstructured":"Homoud A, Das S, Townley S. Comparative Analysis of Deep Learning Model Efficiency for Underwater Video Classification. In: 2025 IEEE International Conference on High Performance Computing and Communications (HPCC), 2025. 1\u20139. https:\/\/doi.org\/10.1109\/hpcc67675.2025.00135","DOI":"10.1109\/HPCC67675.2025.00135"},{"issue":"1","key":"pone.0345593.ref008","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1109\/TIP.2017.2759252","article-title":"Color Balance and Fusion for Underwater Image Enhancement","volume":"27","author":"CO Ancuti","year":"2018","journal-title":"IEEE Trans Image Process"},{"key":"pone.0345593.ref009","doi-asserted-by":"crossref","first-page":"107219","DOI":"10.1016\/j.engappai.2023.107219","article-title":"HFM: A hybrid fusion method for underwater image enhancement","volume":"127","author":"S An","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"12","key":"pone.0345593.ref010","doi-asserted-by":"crossref","first-page":"5664","DOI":"10.1109\/TIP.2016.2612882","article-title":"Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior","volume":"25","author":"Li Chong-Yi","year":"2016","journal-title":"IEEE Trans Image Process"},{"key":"pone.0345593.ref011","first-page":"63","article-title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","volume-title":"Lecture Notes in Computer Science","author":"X Wang","year":"2019"},{"issue":"1","key":"pone.0345593.ref012","doi-asserted-by":"crossref","first-page":"175","DOI":"10.54254\/2755-2721\/83\/2024GLG0065","article-title":"Exploring SRGAN-Based Model for Image Super-Resolution","volume":"83","author":"R Yang","year":"2024","journal-title":"ACE"},{"key":"pone.0345593.ref013","doi-asserted-by":"crossref","DOI":"10.3389\/fmars.2024.1424619","article-title":"DeformableFishNet: a high-precision lightweight target detector for underwater fish identification","volume":"11","author":"Z Ruan","year":"2024","journal-title":"Front Mar Sci"},{"key":"pone.0345593.ref014","first-page":"715","article-title":"Image Enhancement of Underwater Images Using Deep Learning Techniques","volume-title":"Lecture Notes in Networks and Systems","author":"SK Dasari","year":"2023"},{"key":"pone.0345593.ref015","doi-asserted-by":"crossref","first-page":"102290","DOI":"10.1016\/j.aquaeng.2022.102290","article-title":"Underwater abnormal classification system based on deep learning: A case study on aquaculture fish farm in Taiwan","volume":"99","author":"JC Chen","year":"2022","journal-title":"Aquacultural Engineering"},{"key":"pone.0345593.ref016","doi-asserted-by":"crossref","unstructured":"Ueki Y, Ikehara M. Underwater Image Enhancement Based on the Iteration of a Generalization of Dark Channel Prior. In: 2019 IEEE Visual Communications and Image Processing (VCIP), 2019. 1\u20134. 10.1109\/vcip47243.2019.8965726","DOI":"10.1109\/VCIP47243.2019.8965726"},{"issue":"3","key":"pone.0345593.ref017","doi-asserted-by":"crossref","first-page":"3594","DOI":"10.1007\/s10489-022-03767-y","article-title":"Underwater vision enhancement technologies: a comprehensive review, challenges, and recent trends","volume":"53","author":"J Zhou","year":"2022","journal-title":"Appl Intell"},{"issue":"3","key":"pone.0345593.ref018","doi-asserted-by":"crossref","first-page":"3629","DOI":"10.1364\/OE.27.003629","article-title":"Polarization-based exploration for clear underwater vision in natural illumination","volume":"27","author":"F Liu","year":"2019","journal-title":"Opt Express"},{"key":"pone.0345593.ref019","doi-asserted-by":"crossref","first-page":"107737","DOI":"10.1016\/j.optlaseng.2023.107737","article-title":"Robust polarization-based underwater image enhancement method using anchor brightness adaptation","volume":"169","author":"Y Chen","year":"2023","journal-title":"Optics and Lasers in Engineering"},{"key":"pone.0345593.ref020","doi-asserted-by":"crossref","first-page":"105810","DOI":"10.1016\/j.asoc.2019.105810","article-title":"Natural-based underwater image color enhancement through fusion of swarm-intelligence algorithm","volume":"85","author":"KZ Mohd Azmi","year":"2019","journal-title":"Applied Soft Computing"},{"issue":"5","key":"pone.0345593.ref021","doi-asserted-by":"crossref","first-page":"2567","DOI":"10.3390\/s23052567","article-title":"Underwater Object Detection Using TC-YOLO with Attention Mechanisms","volume":"23","author":"K Liu","year":"2023","journal-title":"Sensors (Basel)"},{"key":"pone.0345593.ref022","doi-asserted-by":"crossref","first-page":"72492","DOI":"10.1109\/ACCESS.2019.2920403","article-title":"Single Image Defogging Based on Multi-Channel Convolutional MSRCR","volume":"7","author":"W Zhang","year":"2019","journal-title":"IEEE Access"},{"issue":"6","key":"pone.0345593.ref023","doi-asserted-by":"crossref","first-page":"595","DOI":"10.3390\/math9060595","article-title":"Underwater Image Enhancement Based on Multi-Scale Fusion and Global Stretching of Dual-Model","volume":"9","author":"H Song","year":"2021","journal-title":"Mathematics"},{"key":"pone.0345593.ref024","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LRA.2017.2730363","article-title":"WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images","author":"J Li","year":"2017","journal-title":"IEEE Robot Autom Lett"},{"issue":"12","key":"pone.0345593.ref025","doi-asserted-by":"crossref","first-page":"2341","DOI":"10.1109\/TPAMI.2010.168","article-title":"Single Image Haze Removal Using Dark Channel Prior","volume":"33","author":"K He","year":"2011","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"pone.0345593.ref026","doi-asserted-by":"crossref","first-page":"2856","DOI":"10.1109\/TIP.2018.2813092","article-title":"Generalization of the Dark Channel Prior for Single Image Restoration","volume":"27","author":"Y-T Peng","year":"2018","journal-title":"IEEE Trans Image Process"},{"key":"pone.0345593.ref027","article-title":"An Underwater Image Enhancement Benchmark Dataset and Beyond","author":"C Li","year":"2019","journal-title":"IEEE Trans Image Process"},{"issue":"7","key":"pone.0345593.ref028","doi-asserted-by":"crossref","first-page":"4879","DOI":"10.1109\/TCSVT.2021.3114230","article-title":"GUDCP: Generalization of Underwater Dark Channel Prior for Underwater Image Restoration","volume":"32","author":"Z Liang","year":"2022","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"2","key":"pone.0345593.ref029","doi-asserted-by":"crossref","first-page":"241","DOI":"10.3390\/jmse10020241","article-title":"An Overview of Underwater Vision Enhancement: From Traditional Methods to Recent Deep Learning","volume":"10","author":"K Hu","year":"2022","journal-title":"JMSE"},{"key":"pone.0345593.ref030","doi-asserted-by":"crossref","unstructured":"Srinivas S, Siddharth VR, Dutta S, Khare NS, Krishna L. Channel prior based Retinex model for underwater image enhancement. In: 2022 Second International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), 2022. 1\u201310. https:\/\/doi.org\/10.1109\/icaect54875.2022.9807919","DOI":"10.1109\/ICAECT54875.2022.9807919"},{"key":"pone.0345593.ref031","doi-asserted-by":"crossref","unstructured":"Parihar AS, Singh K. A study on Retinex based method for image enhancement. In: 2018 2nd International Conference on Inventive Systems and Control (ICISC), 2018. 619\u201324. https:\/\/doi.org\/10.1109\/icisc.2018.8398874","DOI":"10.1109\/ICISC.2018.8398874"},{"issue":"5","key":"pone.0345593.ref032","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1007\/s11760-019-01439-y","article-title":"Efficient underwater image and video enhancement based on Retinex","volume":"13","author":"C Tang","year":"2019","journal-title":"SIViP"},{"key":"pone.0345593.ref033","doi-asserted-by":"crossref","unstructured":"Khan A, Ali SSA, Malik AS, Anwer A, Meriaudeau F. Underwater image enhancement by wavelet based fusion. In: 2016 IEEE International Conference on Underwater System Technology: Theory and Applications (USYS), 2016. 83\u20138. https:\/\/doi.org\/10.1109\/usys.2016.7893927","DOI":"10.1109\/USYS.2016.7893927"},{"issue":"2","key":"pone.0345593.ref034","doi-asserted-by":"crossref","first-page":"3227","DOI":"10.1109\/LRA.2020.2974710","article-title":"Fast Underwater Image Enhancement for Improved Visual Perception","volume":"5","author":"MJ Islam","year":"2020","journal-title":"IEEE Robot Autom Lett"},{"key":"pone.0345593.ref035","doi-asserted-by":"crossref","unstructured":"Katayama T, Song T, Shimamoto T, Jiang X. GAN-based color correction for underwater object detection. In: OCEANS 2019 MTS\/IEEE SEATTLE, 2019. 1\u20134.","DOI":"10.23919\/OCEANS40490.2019.8962561"},{"key":"pone.0345593.ref036","doi-asserted-by":"crossref","unstructured":"Zhu J-Y, Park T, Isola P, Efros AA. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), 2017. 2242\u201351. https:\/\/doi.org\/10.1109\/iccv.2017.244","DOI":"10.1109\/ICCV.2017.244"},{"key":"pone.0345593.ref037","doi-asserted-by":"crossref","unstructured":"Sharma R, Kamra A. A Review on CLAHE Based Enhancement Techniques. In: 2023 6th International Conference on Contemporary Computing and Informatics (IC3I), 2023. 321\u20135. https:\/\/doi.org\/10.1109\/ic3i59117.2023.10397722","DOI":"10.1109\/IC3I59117.2023.10397722"},{"key":"pone.0345593.ref038","doi-asserted-by":"crossref","first-page":"128973","DOI":"10.1109\/ACCESS.2020.3009161","article-title":"Underwater Image Enhancement Based on Global and Local Equalization of Histogram and Dual-Image Multi-Scale Fusion","volume":"8","author":"L Bai","year":"2020","journal-title":"IEEE Access"},{"issue":"6","key":"pone.0345593.ref039","doi-asserted-by":"crossref","first-page":"3735","DOI":"10.1007\/s00371-024-03630-w","article-title":"Underwater image restoration and enhancement: a comprehensive review of recent trends, challenges, and applications","volume":"41","author":"YM Alsakar","year":"2024","journal-title":"Vis Comput"},{"key":"pone.0345593.ref040","doi-asserted-by":"crossref","unstructured":"Sukesh M, Muthunayagam M, Latha M. Super-resolution performance: A comparative analysis of SRGAN and ESRGAN techniques for single image restoration. In: 2024 Intelligent Systems and Machine Learning Conference (ISML), 2024. 128\u201334.","DOI":"10.1109\/ISML60050.2024.11007359"},{"key":"pone.0345593.ref041","doi-asserted-by":"crossref","first-page":"121078","DOI":"10.1016\/j.ins.2024.121078","article-title":"ConvFishNet: An efficient backbone for fish classification from composited underwater images","volume":"679","author":"H Qu","year":"2024","journal-title":"Information Sciences"},{"key":"pone.0345593.ref042","doi-asserted-by":"crossref","DOI":"10.3389\/fmars.2023.1151758","article-title":"Automatic detection and classification of coastal Mediterranean fish from underwater images: Good practices for robust training","volume":"10","author":"IA Catal\u00e1n","year":"2023","journal-title":"Front Mar Sci"},{"key":"pone.0345593.ref043","unstructured":"4K UltraHD underwater biodiversity stock footage demo video. 4K Underwater Footage."},{"key":"pone.0345593.ref044","doi-asserted-by":"crossref","unstructured":"Joly A, Go\u00ebau H, Glotin H, Spampinato C, Bonnet P, Vellinga WP. LifeCLEF 2015: multimedia life species identification challenges. In: Experimental IR Meets Multilinguality, Multimodality, and Interaction: 6th International Conference of the CLEF Association, CLEF\u201915, Toulouse, France, September 8-11, 2015, Proceedings, 2015. 462\u201383.","DOI":"10.1007\/978-3-319-24027-5_46"},{"key":"pone.0345593.ref045","doi-asserted-by":"crossref","unstructured":"Homoud A, Das S, Townley S. Challenges in Underwater Object Detection and Video Segmentation Using Deep Learning. In: 2024. 1\u20136.","DOI":"10.1109\/InCoWoCo64194.2024.10863165"},{"issue":"2","key":"pone.0345593.ref046","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1109\/TPAMI.1986.4767773","article-title":"Collision Detection for Moving Polyhedra","author":"J Canny","year":"1986","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"pone.0345593.ref047","doi-asserted-by":"crossref","first-page":"27","DOI":"10.30780\/specialissue-ISET-2024\/023","article-title":"CANNY EDGE DETECTION: A COMPREHENSIVE REVIEW","volume":"9","author":"H Agrawal","year":"2024","journal-title":"IJTRS"},{"key":"pone.0345593.ref048","first-page":"129","article-title":"Deep Learning for Marine Species Recognition","volume-title":"Smart Innovation, Systems and Technologies","author":"L Xu","year":"2019"},{"issue":"6","key":"pone.0345593.ref049","doi-asserted-by":"crossref","first-page":"1846","DOI":"10.3390\/s25061846","article-title":"YOLOv8-TF: Transformer-Enhanced YOLOv8 for Underwater Fish Species Recognition with Class Imbalance Handling","volume":"25","author":"C Shah","year":"2025","journal-title":"Sensors (Basel)"},{"issue":"9","key":"pone.0345593.ref050","doi-asserted-by":"crossref","DOI":"10.1002\/aqc.4241","article-title":"Deep Learning for Multilabel Classification of Coral Reef Conditions in the Indo\u2010Pacific Using Underwater Photo Transect Method","volume":"34","author":"X Shao","year":"2024","journal-title":"Aquatic Conservation"},{"issue":"2","key":"pone.0345593.ref051","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.33395\/sinkron.v8i2.13583","article-title":"Fine-grained analysis of coral instance segmentation using YOLOv8 models","volume":"8","author":"WM Hassanudin","year":"2024","journal-title":"Sinkron: jurnal dan penelitian teknik informatika"},{"issue":"11","key":"pone.0345593.ref052","article-title":"Deep learning-based image classification of sea turtles using object detection and instance segmentation models","volume":"19","author":"J-W Baek","year":"2024","journal-title":"PLoS One"},{"key":"pone.0345593.ref053","doi-asserted-by":"crossref","unstructured":"Adam L, \u010cerm\u00e1k V, Papafitsoros K, Picek L. SeaTurtleID2022: A long-span dataset for reliable sea turtle re-identification. In: 2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), 2024. 7131\u201341. https:\/\/doi.org\/10.1109\/wacv57701.2024.00699","DOI":"10.1109\/WACV57701.2024.00699"},{"key":"pone.0345593.ref054","doi-asserted-by":"crossref","unstructured":"Buades A, Coll B, Morel J-M. A Non-Local Algorithm for Image Denoising. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905). 60\u20135. https:\/\/doi.org\/10.1109\/cvpr.2005.38","DOI":"10.1109\/CVPR.2005.38"},{"issue":"11","key":"pone.0345593.ref055","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"I Goodfellow","year":"2020","journal-title":"Commun ACM"},{"key":"pone.0345593.ref056","doi-asserted-by":"crossref","unstructured":"Zhang R, Isola P, Efros AA, Shechtman E, Wang O. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018. 586\u201395. https:\/\/doi.org\/10.1109\/cvpr.2018.00068","DOI":"10.1109\/CVPR.2018.00068"},{"key":"pone.0345593.ref057","doi-asserted-by":"crossref","unstructured":"Homoud A, Das S, Townley S. Challenges in Underwater Video Data Processing. In: 2025 Eighth International Women in Data Science Conference at Prince Sultan University (WiDS PSU), 2025. 1\u20136.","DOI":"10.1109\/WiDS-PSU64963.2025.00034"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0345593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:57:13Z","timestamp":1774634233000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0345593"}},"subtitle":[],"editor":[{"given":"Don","family":"S","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":57,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0345593","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,27]]}}}