{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T17:12:19Z","timestamp":1793207539731,"version":"4.5.0"},"reference-count":40,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Recep Tayyip Erdo\u011fan University Development Foundation","award":["02025002025305"],"award-info":[{"award-number":["02025002025305"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>The fish market is a crucial industry for both domestic economies and the global seafood trade. Accurate fish species classification (FSC) plays a significant role in ensuring sustainability, improving food safety, and optimizing market efficiency. This study introduces automatic FSC using Swin Transformer (ST) through transfer learning (SwinFishNet), which proposes an innovative approach to FSC by leveraging the ST model, a cutting-edge architecture known for its exceptional performance in computer vision tasks. The ST\u2019s unique ability to capture both local and global features through its hierarchical structure enhances its effectiveness in complex image classification tasks. The model utilizes three distinct datasets: the 12-class BD-Freshwater-Fish dataset, the 10-class SmallFishBD dataset, and the 20-class FishSpecies dataset, focusing on image processing-based classification. Images were preprocessed by resizing to 224 <jats:inline-formula id=\"pone.0322711.e001\"><jats:alternatives><jats:graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" id=\"pone.0322711.e001g\" mimetype=\"image\" position=\"anchor\" xlink:href=\"info:doi\/10.1371\/journal.pone.0322711.e001\" xlink:type=\"simple\"\/><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"inline\" id=\"M1\"><mml:mrow><mml:mi>\u00d7<\/mml:mi><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula> 224 pixels, normalizing, and converting to tensor format for compatibility with deep learning models. Transfer learning was applied using the ST, which was fine-tuned on these datasets and optimized with the AdamW algorithm. The model\u2019s performance was evaluated using classification accuracy (CA), F1-score, recall, precision, Matthews correlation coefficient, Cohen\u2019s kappa and confusion matrix metrics. The results yielded promising CAs: 0.9847 for BD-Freshwater-Fish, 0.9964 for SmallFishBD, and 0.9932 for the FishSpecies dataset. These results underscore the potential of the SwinFishNet in automating FSC and demonstrate its significant contributions to improving sustainability, market efficiency, and food safety in the seafood industry. This work offers a novel methodology with broad applications in both commercial and research settings, advancing the role of artificial intelligence in the fish market.<\/jats:p>","DOI":"10.1371\/journal.pone.0322711","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T17:53:12Z","timestamp":1747763592000},"page":"e0322711","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":11,"title":["SwinFishNet: A Swin Transformer-based approach for automatic fish species classification using transfer learning"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5371-7238","authenticated-orcid":true,"given":"Ebru","family":"Erg\u00fcn","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,5,20]]},"reference":[{"issue":"6","key":"pone.0322711.ref001","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0155634","article-title":"Models of marine fish biodiversity: Assessing predictors from three habitat classification schemes","volume":"11","author":"KL Yates","year":"2016","journal-title":"PLoS ONE"},{"issue":"1","key":"pone.0322711.ref002","doi-asserted-by":"crossref","first-page":"13110","DOI":"10.1038\/s41598-024-63929-5","article-title":"Assessment of sustainable baits for passive fishing gears through automatic fish behavior recognition","volume":"14","author":"AS Abangan","year":"2024","journal-title":"Scientific Reports"},{"issue":"6","key":"pone.0322711.ref003","article-title":"Farmland pest recognition based on Cascade RCNN Combined with Swin-Transformer","volume":"19","author":"R Xu","year":"2024","journal-title":"PLoS ONE"},{"issue":"3","key":"pone.0322711.ref004","doi-asserted-by":"crossref","first-page":"1997","DOI":"10.1007\/s10115-023-01987-3","article-title":"FishRNFuseNET: development of heuristic-derived recurrent neural network with feature fusion strategy for fish species classification","volume":"66","author":"M Bhanumathi","year":"2024","journal-title":"Knowl Inf Syst"},{"key":"pone.0322711.ref005","doi-asserted-by":"crossref","first-page":"41180","DOI":"10.1109\/ACCESS.2024.3376441","article-title":"A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends","volume":"12","author":"A Younesi","year":"2024","journal-title":"IEEE Access"},{"issue":"6","key":"pone.0322711.ref006","doi-asserted-by":"crossref","first-page":"6988","DOI":"10.1007\/s10489-020-02154-9","article-title":"Temperate fish detection and classification: a deep learning based approach","volume":"52","author":"KM Knausg\u00e5rd","year":"2022","journal-title":"Applied Intelligence"},{"issue":"4","key":"pone.0322711.ref007","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0284992","article-title":"Multi-classification deep neural networks for identification of fish species using camera captured images","volume":"18","author":"H Malik","year":"2023","journal-title":"PLoS ONE"},{"key":"pone.0322711.ref008","doi-asserted-by":"crossref","first-page":"100663","DOI":"10.1016\/j.jafr.2023.100663","article-title":"An advanced Bangladeshi local fish classification system based on the combination of deep learning and the internet of things (IoT)","volume":"14","author":"MA Ahmed","year":"2023","journal-title":"Journal of Agriculture and Food Research"},{"key":"pone.0322711.ref009","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"},{"issue":"6","key":"pone.0322711.ref010","article-title":"Research on marine fish classification and recognition based on an optimized ResNet50 model","volume":"16","author":"G Gao","year":"2024","journal-title":"Marine and Coastal Fisheries"},{"issue":"1","key":"pone.0322711.ref011","doi-asserted-by":"crossref","first-page":"71","DOI":"10.21512\/commit.v17i1.8107","article-title":"Fish classification system using YOLOv3-ResNet18 model for mobile phones","volume":"17","author":"S Liawatimena","year":"2023","journal-title":"CommIT Journal"},{"key":"pone.0322711.ref012","unstructured":"Ayyad MN, Abu-Naser SS. Fish Classification Using Deep Learning. International Journal of Academic Information Systems Research. 2024; 8(4):51\u20138."},{"key":"pone.0322711.ref013","article-title":"Fine-Grained Fish Classification From Small to Large Datasets With Vision Transformers","author":"RJ Veiga","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0322711.ref014","first-page":"173","article-title":"Automatic Nile Tilapia fish classification approach using machine learning techniques","author":"MMM Fouad","year":"2013","journal-title":"13th International Conference on Hybrid Intelligent Systems (HIS 2013)"},{"issue":"4","key":"pone.0322711.ref015","first-page":"1862","article-title":"A feature learning and object recognition framework for underwater fish images","volume":"25","author":"MC Chuang","year":"2016","journal-title":"IEEE Transactions on Image Processing"},{"key":"pone.0322711.ref016","first-page":"1135","article-title":"Classification of different types of koi fish using convolutional neural network","author":"MS Cueto","year":"2021","journal-title":"In: 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS)"},{"key":"pone.0322711.ref017","first-page":"96","volume-title":"Koi fish classification based on HSV color space. In: 2016 International Conference on Information & Communication Technology and Systems (ICTS","author":"DSY Kartika","year":"2016"},{"issue":"23","key":"pone.0322711.ref018","first-page":"4387","article-title":"Hybrid genetic algorithm with tabu search with back-propagation algorithm for fish classification: determining the appropriate feature set","volume":"14","author":"MK Alsmadi","year":"2019","journal-title":"International Journal of Applied Engineering Research"},{"issue":"1","key":"pone.0322711.ref019","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.inpa.2021.01.001","article-title":"Tuna classification using super learner ensemble of region-based CNN-grouped 2D-LBP models","volume":"9","author":"JA Jose","year":"2022","journal-title":"Information Processing in Agriculture"},{"key":"pone.0322711.ref020","doi-asserted-by":"crossref","unstructured":"Chhabra HS, Srivastava AK, Nijhawan R. A hybrid deep learning approach for automatic fish classification. In: Proceedings of ICETIT 2019: Emerging Trends in Information Technology, 2020. pp. 427\u2013436.","DOI":"10.1007\/978-3-030-30577-2_37"},{"issue":"4","key":"pone.0322711.ref021","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/s42979-021-00614-8","volume":"2","author":"M Mathur","year":"2021","journal-title":"SN Computer Science"},{"key":"pone.0322711.ref022","doi-asserted-by":"crossref","unstructured":"K Khotimah, A Arifin, A Yuniarti, A Wijaya, D Navastara, M Kalbuadi. Tuna fish classification using decision tree algorithm and image processing method. In: 2015 International Conference on Computer, Control, Informatics and its Applications (IC3INA). 2015. pp. 126\u2013131.","DOI":"10.1109\/IC3INA.2015.7377759"},{"key":"pone.0322711.ref023","first-page":"1","article-title":"Underwater fish species classification using convolutional neural network and deep learning","author":"D Rathi","year":"2017","journal-title":"2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR)"},{"key":"pone.0322711.ref024","doi-asserted-by":"crossref","unstructured":"Islam MA, Howlader MR, Habiba U, Faisal RH, Rahman MM. Indigenous fish classification of Bangladesh using hybrid features with SVM classifier. In: 2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2). 2019. pp. 1\u20134.","DOI":"10.1109\/IC4ME247184.2019.9036679"},{"key":"pone.0322711.ref025","doi-asserted-by":"crossref","first-page":"109930","DOI":"10.1016\/j.jfoodeng.2020.109930","article-title":"Smart deep learning-based approach for non-destructive freshness diagnosis of common carp fish","volume":"278","author":"A Taheri-Garavand","year":"2020","journal-title":"Journal of Food Engineering"},{"key":"pone.0322711.ref026","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et al. Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"1","key":"pone.0322711.ref027","doi-asserted-by":"crossref","first-page":"18664","DOI":"10.1038\/s41598-022-21017-6","article-title":"A Swin Transformer-based model for mosquito species identification","volume":"12","author":"D-Z Zhao","year":"2022","journal-title":"Scientific Reports"},{"key":"pone.0322711.ref028","doi-asserted-by":"crossref","first-page":"108041","DOI":"10.1016\/j.engappai.2024.108041","article-title":"SwinT-SRNet: Swin transformer with image super-resolution reconstruction network for pollen images classification","volume":"133","author":"B Zu","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"3","key":"pone.0322711.ref029","article-title":"Small object detection algorithm incorporating swin transformer for tea buds","volume":"19","author":"M Shi","year":"2024","journal-title":"PLoS ONE"},{"key":"pone.0322711.ref030","doi-asserted-by":"crossref","first-page":"111132","DOI":"10.1016\/j.dib.2024.111132","article-title":"BD-freshwater-fish: An image dataset from Bangladesh for AI-powered automatic fish species classification and detection toward smart aquaculture","volume":"57","author":"PK Das","year":"2024","journal-title":"Data in Brief"},{"key":"pone.0322711.ref031","article-title":"BD-Freshwater-Fish: An Image Dataset from Bangladesh for AI-Powered Automatic Fish Species Classification and Detection toward Smart Aquaculture.","year":"2024"},{"key":"pone.0322711.ref032","unstructured":"MFerdaus, RPrito, MAhmed, SRAOhona, KGMorshed, IJJarin, et al. SmallFishBD: A Comprehensive Image Dataset of Common Small Fish Varieties in Bangladesh for Species Identification and Classification. Mendeley Data. 2024; V2. https:\/\/doi.org\/10.17632\/8jvxtvz52x.2"},{"key":"pone.0322711.ref033","article-title":"Comprehensive smartphone image dataset for fish species identification in Bangladesh\u2019s freshwater ecosystems","author":"S Sunny","year":"2025","journal-title":"Mendeley Data"},{"key":"pone.0322711.ref034","doi-asserted-by":"crossref","first-page":"108041","DOI":"10.1016\/j.engappai.2024.108041","article-title":"SwinT-SRNet: Swin transformer with image super-resolution reconstruction network for pollen images classification","volume":"133","author":"B Zu","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"4","key":"pone.0322711.ref035","doi-asserted-by":"crossref","first-page":"2589","DOI":"10.1007\/s00371-023-02939-2","article-title":"A data efficient transformer based on Swin Transformer","volume":"40","author":"D Yao","year":"2024","journal-title":"The Visual Computer"},{"issue":"11","key":"pone.0322711.ref036","doi-asserted-by":"crossref","first-page":"8077","DOI":"10.1007\/s11760-024-03452-2","article-title":"Deep learning-based multiclass classification for citrus anomaly detection in agriculture","volume":"18","author":"E Erg\u00fcn","year":"2024","journal-title":"Signal Image Video Process"},{"key":"pone.0322711.ref037","doi-asserted-by":"crossref","DOI":"10.1007\/s00202-024-02691-3","article-title":"Artificial intelligence approaches for accurate assessment of insulator cleanliness in high-voltage electrical systems","author":"E Erg\u00fcn","year":"2024","journal-title":"Electrical Engineering"},{"issue":"2","key":"pone.0322711.ref038","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1109\/TCDS.2020.3028785","article-title":"A hybrid BCI using singular value decomposition values of the fast Walsh\u2013Hadamard transform coefficients","volume":"15","author":"E Erg\u00fcn","year":"2020","journal-title":"IEEE Trans Cogn Dev Syst"},{"issue":"1","key":"pone.0322711.ref039","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/s13040-023-00322-4","article-title":"The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification","volume":"16","author":"D Chicco","year":"2023","journal-title":"BioData Mining"},{"key":"pone.0322711.ref040","doi-asserted-by":"crossref","first-page":"164386","DOI":"10.1109\/ACCESS.2019.2953104","article-title":"A simplified Cohen\u2019s Kappa for use in binary classification data annotation tasks","volume":"7","author":"J Wang","year":"2019","journal-title":"IEEE Access"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0322711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T17:53:28Z","timestamp":1747763608000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0322711"}},"subtitle":[],"editor":[{"given":"Fatih","family":"Uysal,","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,5,20]]},"references-count":40,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5,20]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0322711","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,20]]}}}