Abstract
Fishes are the one of the most important group of cold blooded vertebrates. They have great nutritional, economical, medicinal and industrial importance. Fish provides many nutrients and micronutrients that are essential to the overall development of body and are an important part of a healthy diet. So it is of utmost importance that we should be able to identify the most important species of fishes and differentiate between them. This differentiation can be very useful to people like doctors, marine biologists or the people working in fishing industry. This work aims to propose a fish classification system that works in natural underwater environment which helps to detect fishes with medicinal or nutritional importance. In this study, we use a hybrid deep learning model where a pre-trained VGG16 model is used for Feature Extraction and Stacking ensemble model is used to detect and classify fishes from images. Distinct classes of 8 different species of fish i.e. Cod, Mackerel, Platy, Pollock, Salmon, Swordtail, Tilapia, Zebra Danio consisting of 435 images were used to test the system. As there was no open-source existing dataset relating these species of fishes we have created our own dataset. Our proposed work has been compared with the other state-of-the-art algorithms (kNN, SVM, RF and Tree) and have outperformed them with a classification accuracy of 93.8%.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ruxton, C.H.S., Reed, S.C., Simpson, M.J.A., Millington, K.J.: The health benefits of omega-3 polyunsaturated fatty acids: a review of the evidence. J. Hum. Nutr. Diet. 17(5), 449–459 (2004)
Malesa-Ciećwierz, M., Usydus, Z.: Vitamin D: can fish food–based solutions be used for reduction of vitamin D deficiency in Poland? Nutrition 31(1), 187–192 (2015)
Djoussé, L., Akinkuolie, A.O., Wu, J.H., Ding, E.L., Gaziano, J.M.: Fish consumption, omega-3 fatty acids and risk of heart failure: a meta-analysis. Clin. Nutr. 31(6), 846–853 (2012)
Chowdhury, R., Stevens, S., Gorman, D., Pan, A., Warnakula, S., Chowdhury, S., Ward, H., Johnson, L., Crowe, F., Hu, F.B., Franco, O.H.: Association between fish consumption, long chain omega 3 fatty acids, and risk of cerebrovascular disease: systematic review and meta-analysis. BMJ 345, e6698 (2012)
Raji, C.A., Erickson, K.I., Lopez, O.L., Kuller, L.H., Gach, H.M., Thompson, P.M., Riverol, M., Becker, J.T.: Regular fish consumption and age-related brain gray matter loss. Am. J. Prev. Med. 47(4), 444–451 (2014)
Ogunlana, S.O., Olabode, O., Oluwadare, S.A.A., Iwasokun, G.B.: Fish classification using support vector machine. Afr. J. Comput. ICT 8(2), 75–82 (2015)
Spampinato, C., Giordano, D., Di Salvo, R., Chen-Burger, Y.H.J., Fisher, R.B., Nadarajan, G.: Automatic fish classification for underwater species behavior understanding. In: Proceedings of the First ACM International Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams, pp. 45–50. ACM (2010)
Lee, D.J., Redd, S., Schoenberger, R., Xu, X., Zhan, P.: An automated fish species classification and migration monitoring system. In: 29th Annual Conference of the IEEE Industrial Electronics Society, IECON 2003 (IEEE Cat. No. 03CH37468), vol. 2, pp. 1080–1085. IEEE (2003)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Lee, Y.: Handwritten digit recognition using K nearest-neighbor, radial-basis function, and backpropagation neural networks. Neural Comput. 3(3), 440–449 (1991)
Ben-Hur, A., Horn, D., Siegelmann, H.T., Vapnik, V.: Support vector clustering. J. Mach. Learn. Res. 2(Dec), 125–137 (2001)
Freund, Y., Schapire, R., Abe, N.: A short introduction to boosting. J. Jpn. Soc. Artif. Intell. 14(771–780), 1612 (1999)
Bosch, A., Zisserman, A., Munoz, X.: Image classification using random forests and ferns. In: 2007 IEEE 11th International Conference on Computer Vision, pp. 1–8. IEEE (2007)
Nijhawan, R., Sharma, H., Sahni, H., Batra, A.: A deep learning hybrid CNN framework approach for vegetation cover mapping using deep features. In: 2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), pp. 192–196. IEEE (2017)
Nijhawan, R., Das, J., Raman, B.: A hybrid of deep learning and hand-crafted features based approach for snow cover mapping. Int. J. Remote Sens. 40(2), 759–773 (2019)
Nijhawan, R., Verma, R., Bhushan, S., Dua, R., Mittal, A.: An integrated deep learning framework approach for nail disease identification. In: 2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), pp. 197–202. IEEE (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Chhabra, H.S., Srivastava, A.K., Nijhawan, R. (2020). A Hybrid Deep Learning Approach for Automatic Fish Classification. In: Singh, P., Panigrahi, B., Suryadevara, N., Sharma, S., Singh, A. (eds) Proceedings of ICETIT 2019. Lecture Notes in Electrical Engineering, vol 605. Springer, Cham. https://doi.org/10.1007/978-3-030-30577-2_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-30577-2_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30576-5
Online ISBN: 978-3-030-30577-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)