DERİN ÖĞRENME İLE BALIK TÜRLERİNİN TESPİTİ

Year 2021, , 569 - 576, 30.12.2021

Kıyas Kayaalp , Sedat Metlek

https://doi.org/10.46519/ij3dptdi.956221

Cited By: 1

Abstract

Beslenmemizde önemli bir yere sahip olan deniz ürünleri, mükemmel bir vitamin ve mineral kaynağıdır. Protein kaynakları içerisinde sindirilmesi oldukça kolay olan deniz mahsulleri, diğer yüksek proteinli kaynaklara göre oldukça az zararlı yağ içermektedir. Balıklarda bulunan omega-3 gibi yağ asitlerinin, insan sağlığını olumsuz etkileyen kalp ve damar hastalıklarından, diyabet ve kanser gibi daha birçok hastalığa iyi geldiği bilinmektedir. Bunun yanı sıra az da olsa insan sağlığını tehdit edebilecek balık türleri de bulunmaktadır. Gerçekleştirilen çalışma ile günümüzün popüler makine öğrenme yöntemlerinden birisi olan derin öğrenme algoritmaları vasıtasıyla, insanoğlunun beslenmesinde önemli bir role sahip olan balıkların, görüntüleri üzerinden türlerinin tahmin edilmesi amaçlanmıştır. Bu amaç doğrultusunda geliştirilen uygulamada, farklı ortamlardan elde edilen 4410 adet balık görüntüsü kullanılmıştır. Kullanılan balık görüntüleri, 483 adet farklı türden oluşmakla beraber, farklı koşullar altında elde edilen gerçek balık görüntüleridir. Çalışmada hazırlanan derin öğrenme algoritmasının eğitim ve test işlemleri için “QUT FISH” veri seti kullanılmıştır. Derin öğrenme yöntemlerinde sıkça kullanılan, Evrişimsel sinir ağları yöntemi ile veri setindeki görüntülerden, balık türlerine ait öznitelikler çıkartılmıştır. Çıkartılan bu öznitelikler çok katmanlı bir yapay sinir ağı modeli ile sınıflandırılmıştır. Yapılan çalışma ile sınıflandırma başarısı olarak %73,72 değeri elde edilmiştir.

Keywords

Derin Öğrenme., Evrişimsel Sinir Ağları, Balık türlerinin tespiti

PREDICTION OF FISH SPECIES WITH DEEP LEARNING

Abstract

Seafood, which has an important place in our diet, is an excellent source of vitamins and minerals. Seafood, which is very easy to digest among protein sources, contains very little harmful fat compared to other high-protein sources. It is known that fatty acids such as omega-3 in fish are effective not only in cardiovascular diseases, but also in important diseases such as diabetes and cancer, which adversely affect human health. In addition, there are also fish species that can threaten human health, albeit a little. By this study, it is aimed to predict fish species by using images of fish that have an important role in human nutrition thanks to deep learning algorithms, one of today's popular machine learning methods. In the application developed for this purpose, 4410 fish images obtained from different environments are used. Fish images of 483 different species are obtained from different environments. The "QUT FISH Dataset" dataset is used for the training and testing of the deep learning algorithm prepared in the study. By means of the Convolutional Neural Networks method, which is frequently used in deep learning methods, the features of fish species are extracted from the data set. These extracted features are classified with a multilayer artificial neural network model. With the study, a value of 73.72% is obtained as classification success.

Keywords

Deep learning, Convolutional neural network, Prediction of fish types

References

• 1. Hridayami, P., Putra, I. K. G. D., and Wibawa, K. S., “Fish species recognition using VGG16 deep convolutional neural network”, J. Comput. Sci. Eng., Vol. 13, No. 3, Pages 124–130, 2019.
• 2. Meissa, B., and Gascuel, B., “Overfishing of marine resources: some lessons from the assessment of demersal stocks off Mauritania”, ICES J. Mar. Sci., Vol. 72, No. 2, Pages 414–427, 2015.
• 3. Le Pape, O., Bonhommeau, S., Nieblas, A.-E. and Fromentin, J.-M. “Overfishing causes frequent fish population collapses but rare extinctions”, Proc. Natl. Acad. Sci., Vol. 114, No. 31, Pages 6274–6284, 2017.
• 4. Davidson, L. N. K., Krawchuk, M. A., and Dulvy, N. K., “Why have global shark and ray landings declined: improved management or overfishing?”, Fish, Vol. 17, No. 2, Pages 438–458, 2016.
• 5. Hussain, M. A., Saputra, T., Szabo, E. A., and Nelan, B., “An overview of seafood supply, food safety and regulation in New South Wales, Australia”, Foods, Vol. 6, No. 7, Pages 52-59, 2017.
• 6. Partis, L. and Wells, R. J., “Identification of fish species using random amplified polymorphic DNA (RAPD)”, Mol. Cell. Probes, Vol. 10, No. 6, Pages 435–441, 1996.
• 7. Saitoh, T., Shibata, T., and Miyazono, T., “Feature points based fish image recognition”, Int. J. Comput. Inf. Syst. Ind. Manag. Appl., Vol. 8, Pages 12–22, 2016.
• 8. Hasija, S., Buragohain, M. J., and Indu, S., “Fish species classification using graph embedding discriminant analysis”, in 2017 International Conference on Machine Vision and Information Technology (CMVIT), 2017, Pages 81–86.
• 9. Meng, L., Hirayama, T., and Oyanagi, S., “Underwater-drone with panoramic camera for automatic fish recognition based on deep learning”, IEEE Access, Vol. 6, Pages 17880–17886, 2018.
• 10. Kılınç, E. E., and Metlek, S., “Su Altı Görüntülerinden Nesne Tespiti”, Avrupa Bilim ve Teknol. Derg., No. 23, Sayfa 368–375, 2021.
• 11. Larsen, R., Olafsdottir, H., and Ersbøll, B. K., “Shape and texture based classification of fish species”, in Scandinavian Conference on Image Analysis, Pages 745–749, 2009.
• 12. Badawi, U. A., and Alsmadi, M. K., “A General fish classification methodology using meta-heuristic algorithm with back propagation classifier”, J. Theor. Appl. Inf. Technol., Vol. 66, No. 3, Pages 76-87, 2014.
• 13. Qin, H., Li, X., Liang, J., Peng, Y., and Zhang, C., “DeepFish: Accurate underwater live fish recognition with a deep architecture”, Neurocomputing, Vol. 187, Pages 49–58, 2016.
• 14. Roberts, P. L. D., Jaffe, J. S., and Trivedi, M. M., “Multiview, broadband acoustic classification of marine fish: a machine learning framework and comparative analysis”, IEEE J. Ocean. Eng., Vol. 36, No. 1, Pages 90–104, 2011.
• 15. Liu, S., “Embedded online fish detection and tracking system via YOLOv3 and parallel correlation filter”, in OCEANS 2018 MTS/IEEE Charleston, Pages 1–6, 2018.
• 16. Pettersen, R., Braa, H. L., Gawel, B. A., Letnes, P. A., Sæther, K., and Aas, L. M. S., “Detection and classification of Lepeophterius salmonis (Krøyer, 1837) using underwater hyperspectral imaging”, Aquac. Eng., Vol. 87, Pages 102-125, 2019.
• 17. İşçimen, B., Kutlu, Y., Reyhaniye, A. N., and Turan, C., “Image analysis methods on fish recognition”, in 2014 22nd Signal Processing and Communications Applications Conference (SIU), Pages 1411–1414, 2014.
• 18. Robotham, H., Castillo, J., Bosch, P., and Perez-Kallens, J., “A comparison of multi-class support vector machine and classification tree methods for hydroacoustic classification of fish-schools in Chile”, Fish. Res., Vol. 111, No. 3, Pages 170–176, 2011.
• 19. Pornpanomchai, C., Lurstwut, B., Leerasakultham, P., and Kitiyanan, V., “Shape-and texture-based fish image recognition system”, Agric. Nat. Resour., Vol. 47, No. 4, Pages 624–634, 2013.
• 20. Kayaalp, K. and Süzen, A. A., “Derin Öğrenme ve Türkiye’deki Uygulamaları”, Yayın Yeri IKSAD Int. Publ. House, Basım sayısı, Vol. 1, 2018.
• 21. Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y., "Deep learning", Vol. 1, no. 2. MIT Press Cambridge, 2016.
• 22. Kemaloğlu, N., and Sevli, O., “Evrişimsel Sinir Ağları ile İşaret Dili Tanıma”, Proceedings on 2nd International Conference on Technology and Science, Sayfa 942-948, Burdur, 2019.
• 23. Rao, B. S., “Accurate leukocoria predictor based on deep VGG-net CNN technique”, IET Image Process., Vol. 14, No. 10, Pages 2241–2248, 2020.
• 24. Tang, P., Wang, H., and Kwong, S., “G-MS2F: GoogLeNet based multi-stage feature fusion of deep CNN for scene recognition”, Neurocomputing, Vol. 225, Pages 188–197, 2017.
• 25. Minhas, R. A., Javed, A., Irtaza, A., Mahmood, M. T., and Joo, Y. B., “Shot classification of field sports videos using AlexNet Convolutional Neural Network”, Appl. Sci., Vol. 9, No. 3, Pages 483-495, 2019.
• 26. Metlek, S., and Kayaalp, K., “Derin Öğrenme ve Destek Vektör Makineleri İle Görüntüden Cinsiyet Tahmini”, Düzce Üniversitesi Bilim ve Teknol. Derg., Vol. 8, No. 3, Pages 2208–2228, 2020.
• 27. Ma, Z., “Fine-grained vehicle classification with channel max pooling modified CNNs”, IEEE Trans. Veh. Technol., Vol. 68, No. 4, Pages 3224–3233, 2019.
• 28. Wang, S.-H., and Chen, Y., “Fruit category classification via an eight-layer convolutional neural network with parametric rectified linear unit and dropout technique”, Multimed. Tools Appl., Vol. 79, No. 21, Pages 15117–15133, 2020.
• 29. Yıldırım, P., Birant, D., and Alpyildiz, T., “Data mining and machine learning in textile industry,” Wiley Interdiscip. Rev. Data Min. Knowl. Discov., Vol. 8, No. 1, Pages 1228-1239, 2018.
• 30. Abdullahi, H. S., Sheriff, R., and Mahieddine, F., “Convolution neural network in precision agriculture for plant image recognition and classification” in 2017 Seventh International Conference on Innovative Computing Technology (INTECH), Vol. 10, Pages 256-272, 2017.
• 31. Mason, K., Duggan, J., and Howley, E., “A multi-objective neural network trained with differential evolution for dynamic economic emission dispatch”, Int. J. Electr. Power Energy Syst., Vol. 100, Pages 201–221, 2018.
• 32. Zermane, H., and Aitouche, S., “Digital learning with covid-19 in Algeria”, Int. J. 3D Print. Technol. Digit. Ind., Vol. 4, no. 2, Pages 161–170, 2020.
• 33. Elmas, Ç., “Yapay sinir ağları”, Sayfa 10-50, Seçkin Yayınları, İstanbul, 2003.
• 34. Emeksiz, C., Doğan, Z., Gökrem, L., and Yavuz, A. H., “Tokat bölgesi rüzgar karakteristiğinin istatistiksel yöntemler ile incelenmesi”, Politek. Derg., Vol. 19, No. 4, Sayfa 481–489, 2016.
• 35. Metlek, S., and Yılmaz, T., “Analysis of Perceived Service Quality and Customer Satisfaction in the Aviation Sector with Artificial Neural Networks, 2”, in Techno-Science, 2nd Internatioanl Conference on Technology and Science, Pages 853–864, 2019.
• 36. Iqbal, M. A., Wang, Z., Ali, Z. A., and Riaz, S., “Automatic fish species classification using deep convolutional neural networks”, Wirel. Pers. Commun., Vol. 116, no. 2, Pages 1043–1053, 2021.
• 37. Ju, Z. and Xue, Y., “Fish species recognition using an improved AlexNet model,” Optik (Stuttg)., Vol. 223, p. 165499, 2020.
• 38. Amanullah Baloch, D., Ali, M., Gül, F., Basir, S., and Afzal, I., “Fish Image Segmentation Algorithm (FISA) for Improving the Performance of Image Retrieval System”, International Journal of Advanced Computer Science and Applications, Vol. 8, No. 12, Pages 396-403, 2017.
• 39. Qiu, C., Zhang, S., Wang, C., Yu, Z., Zheng, H., and Zheng, B., “Improving transfer learning and squeeze-and-excitation networks for small-scale fine-grained fish image classification”, IEEE Access, Vol. 6, Pages 78503–78512, 2018.
• 40. Mathur, M. and Goel, N., “FishResNet: Automatic Fish Classification Approach in Underwater Scenario”, SN Comput. Sci., Vol. 2, No. 4, Pages 1–12, 2021.
• 41. Adiwinata, Y., Sasaoka, A., Bayupati, I. P. A., and Sudana, O., “Fish Species Recognition with Faster R-CNN Inception-v2 using QUT FISH Dataset”, Lontar Komput. J. Ilm. Teknolologi Inf., Vol. 11, No. 3, Pages 144-160, 2020.
• 42. Guo, Z., “Few-shot Fish Image Generation and Classification”, in Global Oceans 2020: Singapore–US Gulf Coast, Pages 1–6, 2020.
• 43. Sarıgül, M., and Avcı, M., “Comparison of different deep structures for fish classification”, Int. J. Comput. Theory Eng., Vol. 9, No. 5, Pages 362–366, 2017.