{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T11:45:14Z","timestamp":1762429514831,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T00:00:00Z","timestamp":1648857600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T00:00:00Z","timestamp":1648857600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"national natural science foundation of china","doi-asserted-by":"publisher","award":["41906176"],"award-info":[{"award-number":["41906176"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hainan Provincial Natural Science Foundation of China","award":["419QN172"],"award-info":[{"award-number":["419QN172"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Earth Sci Inform"],"published-print":{"date-parts":[[2022,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Seafloor unconstrained environment video is shot in uncontrolled open sea area. There are multiple backgrounds, complex illumination and weather changes, and rapid growth of algae and attached lenses, which affect the stability of video shooting quality, resulting in difficulty in image recognition. At present, there is still no algorithm that is superior to other methods generally, and it is necessary to build a model combined with specific scenes and applications. In this paper, a fish identification method in tropical waters based on transfer learning under unconstrained environment is proposed. Firstly, the image is pre-processed by affine transformation to realize data enhancement. Furthermore, RestNet50 deep convolutional neural network is constructed based on transfer learning to compare the effect of fish recognition before and after transfer learning. The results show that, the accuracy and loss indicators are better than those of non-transfer learning when the trained model of imagenet is introduced as the initial weight of the network. When the model is trained to 150 epochs, the indicators begin to converge, which can better complete the fish identification task in tropical waters under unconstrained environment.<\/jats:p>","DOI":"10.1007\/s12145-022-00783-x","type":"journal-article","created":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T07:38:30Z","timestamp":1648885110000},"page":"1155-1166","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Research on fish identification in tropical waters under unconstrained environment based on transfer learning"],"prefix":"10.1007","volume":"15","author":[{"given":"Shan","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Weifang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yupeng","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Jianqiang","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,4,2]]},"reference":[{"key":"783_CR1","unstructured":"Alsmadi M K A,Omar K B,Noah S A, et al (2016) Fish recognition based on the combination between robust features selection,image segmentation and geometrical parameters techniques using artificial neural network and decision tree[J].International Journal of Computer Science and Information Security,2016,6(2):215\u2013221"},{"key":"783_CR2","unstructured":"Chomtip P,Pimprapai L,Waranat K, et al (2016) Thai fish image recognition system[C]\/\/The Proceedings of International Joint Conference on Computer Science and Software Engineering. Bangkok, Thailand.2016:115\u2013120"},{"issue":"1","key":"783_CR3","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1109\/TCSVT.2014.2357093","volume":"25","author":"MC Chuang","year":"2015","unstructured":"Chuang MC, Hwang JN, Williams K et al (2015) Tracking live fish from low contrast and low-frame-rate stereo videos. IEEE Trans Circuits Syst Video Technol 25(1):167\u2013179","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"783_CR4","unstructured":"Ciresan D, Giusti A, Gambardella LM et al (2012) Deep neural networks segment neuronal membranes in electron microscopy images. Adv Neural Inf Proces Syst:2843\u20132851"},{"key":"783_CR5","doi-asserted-by":"crossref","unstructured":"Dai W , Yang Q , Xue G R , et al. (2007) Boosting for Transfer Learning[C]\/\/ Machine Learning, Proceedings of the 24th International Conference (ICML 2007), Corvallis, Oregon, USA, June 20-24, 2007. 193\u2013200","DOI":"10.1145\/1273496.1273521"},{"key":"783_CR6","doi-asserted-by":"crossref","unstructured":"Evans FH. 2003. Detecting fish in underwater video using the EM algorithm. International Conference on Image Processing, 3(III): 1029\u20131032","DOI":"10.1109\/ICIP.2003.1247423"},{"key":"783_CR7","doi-asserted-by":"crossref","unstructured":"Fisher, R., Chen-Burger, Y., Giordano, D., Hardman, L., Lin, F., 2016. Fish4Knowledge: Collecting and Analyzing Massive Coral Reef Fish Video Data , Intelligent Systems Reference Library. Springer International Publishing URL. https:\/\/books.google. com.pk\/books?id=j846jwEACAAJ","DOI":"10.1007\/978-3-319-30208-9"},{"key":"783_CR8","doi-asserted-by":"crossref","unstructured":"Frederic M, Alvarez LM, Hodgson A. 2015. Automating marine mammal detection in aerial images captured during wildlife surveys: a deep learning approach. Australasian Joint Conference on Artificial Intelligence, 379-385","DOI":"10.1007\/978-3-319-26350-2_33"},{"key":"783_CR9","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T et al (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. IEEE Conference on computer vision and pattern recognition 2014:580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"783_CR10","unstructured":"Hinton GE, Srivastava N, Krizhevsky A et al (2012) Improving neural networks by preventing co-adaptation of feature detectors[J]. arXiv e-prints"},{"key":"783_CR11","unstructured":"Hodgson G (2001) Reef Check: The first step in community-based management[J]. Bulletin of Marine Science -Miami-"},{"issue":"9","key":"783_CR12","first-page":"13","volume":"23","author":"YH Hsiao","year":"2013","unstructured":"Hsiao YH, Chen CC, Lin SI et al (2013) Real-world underwater fish recognition identification,using sparse representation[J]. Ecological Informatics 23(9):13\u201321","journal-title":"Ecological Informatics"},{"key":"783_CR13","doi-asserted-by":"crossref","unstructured":"Jager J, Wolff V, Fricke NK et al (2017) Visual fish tracking: Combining a two-stage graph approach with CNN-features. IEEE OCEANS:1\u20136","DOI":"10.1109\/OCEANSE.2017.8084691"},{"key":"783_CR14","doi-asserted-by":"crossref","unstructured":"Lawrence ND, Plat JC (2004) Learning to learn with the informative vector machine[C]\/\/Machine Learning, Proceedings of the 21stst International Conference (ICML 2004). New York:ACM:65\u201372","DOI":"10.1145\/1015330.1015382"},{"key":"783_CR15","doi-asserted-by":"crossref","unstructured":"Lee SI, Chatalbashev V, Vickrey D (2007) Koller D.Leaming a meta\u2014level prior for feature relevance from multiple related tasks[C]\/\/Machine Learning, Proceedings of the 24th International Conference (ICML 2007), Corvallis, Oregon, USA, June 20-24, 2007.489\u2013496","DOI":"10.1145\/1273496.1273558"},{"issue":"09","key":"783_CR16","first-page":"34","volume":"43","author":"HT Li","year":"2019","unstructured":"Li HT, Liu TL, Shao ZD (2019) Application of a BP neural network based on decision tree and two partition algorithm in prediction of red tide severity[J]. Mar Sci 43(09):34\u201340","journal-title":"Mar Sci"},{"issue":"3","key":"783_CR17","doi-asserted-by":"publisher","first-page":"619","DOI":"10.3724\/SP.J.1118.2011.00619","volume":"8","author":"YZ Li","year":"2011","unstructured":"Li YZ, Shi ZR, Ai H et al (2011) Large scale distribution patterns of taxonomic diversity of fish in coral reef waters, South China Sea[J]. Journal of Fishery Sciences of China 8(3):619\u2013628","journal-title":"Journal of Fishery Sciences of China"},{"key":"783_CR18","doi-asserted-by":"crossref","unstructured":"Spampinato C., Palazzo S., Giordano D., et al.2012. Covariance based fish tracking in real-life underwater environment. International Conference on Computer Vision Theory and Applications, 409\u2013414","DOI":"10.5220\/0003866604090414"},{"key":"783_CR19","unstructured":"Szegedy C, Toshev A, Erhan D (2013) Deep neural networks for object detection. Adv Neural Inf Proces Syst:2553\u20132561"},{"key":"783_CR20","doi-asserted-by":"crossref","unstructured":"Toh YH., Ng TM., Liew BK. 2009. Automated fish counting using image processing. International Conference on Computational Intelligence and Software Engineering, 1\u20135","DOI":"10.1109\/CISE.2009.5365104"},{"key":"783_CR21","doi-asserted-by":"crossref","unstructured":"Wang SH, Zhao JW, Chen YQ (2017) Robust tracking of fish schools using CNN for head identification. Multimed Tools Appl:86\u2013105","DOI":"10.1007\/s11042-016-4045-3"},{"issue":"2","key":"783_CR22","first-page":"268","volume":"41","author":"YD Xiao","year":"2015","unstructured":"Xiao YD, Cai SZ (2015) Design of Mobile Video Surveillance Software Based on iOS Platform[J]. Comput Eng 41(2):268\u2013271","journal-title":"Comput Eng"},{"key":"783_CR23","doi-asserted-by":"crossref","unstructured":"Xu Y, Du J, Dai LR, et al (2015) A regression approach to speech enhancement based on deep neural networks[J]. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 7\u201319","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"783_CR24","unstructured":"Yang H S (2015) The principle and practice of constructing marine ranch[M].Beijing: science press.2015"},{"key":"783_CR25","unstructured":"Yu K., Jia L., Chen Y Q, et al (2013) Deep Learning: Yesterday, Today, and tomorrow[J]. Journal of Computer Research and development, 26.,2013, 50(9): 1799\u20131804"},{"issue":"17","key":"783_CR26","first-page":"738","volume":"55","author":"S Zhang","year":"2017","unstructured":"Zhang S, Zhu Y (2017) Research on the Construction of Underwater Video Surveillance and Water Environment Monitoring Information System for Marine Ranching[J]. Bolet\u00edn T\u00e9cnico 55(17):738\u2013742","journal-title":"Bolet\u00edn T\u00e9cnico"},{"key":"783_CR27","unstructured":"Zhang S, Zhu Y P (2018) Simulation of Regional Species Identification of Marine Organisms Based on 3D Vision[J]. Computer Simulation, 29.2018.35(5) : 402\u2013406+443"},{"key":"783_CR28","unstructured":"Zhang S, Zhu Y, Bin Y (2019) Tropical coral reef fish identification method based on ResNet in unconstrained environment of the seabed[J], Revista Cient\u00edfica\u00a02019(107):1157\u20131164"},{"key":"783_CR29","first-page":"60","volume":"2","author":"SM Zhang","year":"2020","unstructured":"Zhang SM, Liu Y, Fan W et al (2020) Aquarium fish target detection APP development based on TensorFlow[J]. Fishery Modernization 2:60\u201367","journal-title":"Fishery Modernization"},{"key":"783_CR30","doi-asserted-by":"crossref","unstructured":"Zhou X., Xie L., Zhang P. 2015. Online object tracking based on CNN with metropolis-hasting re-sampling. Proceedings of the ACM international conference on multimedia, 1\u20134","DOI":"10.1145\/2733373.2806307"},{"issue":"2","key":"783_CR31","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.aquaeng.2008.01.002","volume":"38","author":"B Zion","year":"2008","unstructured":"Zion B, Alchanatis V, Ostrovsky V, Barki A, Karplus I (2008) Classification of guppies Poecilia reticulata gender by computer vision[J]. Aquac Eng 38(2):97\u2013104","journal-title":"Aquac Eng"}],"container-title":["Earth Science Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12145-022-00783-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12145-022-00783-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12145-022-00783-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,21]],"date-time":"2024-09-21T13:37:26Z","timestamp":1726925846000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12145-022-00783-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,2]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["783"],"URL":"https:\/\/doi.org\/10.1007\/s12145-022-00783-x","relation":{},"ISSN":["1865-0473","1865-0481"],"issn-type":[{"type":"print","value":"1865-0473"},{"type":"electronic","value":"1865-0481"}],"subject":[],"published":{"date-parts":[[2022,4,2]]},"assertion":[{"value":"31 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}