Journals / Aquatic Sciences and Engineering / 2022 / Cilt: 37 - Sayı: 4

Multi-species Fish Identification using Hybrid DeepCNN with Refined Squeeze and Excitation Architecture

Pages
220–228
Publication Date
2022-10-20
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Then post-training with the small-scale dataset (Croatian) achieved an accuracy of 94.99% with an 11% improvement compared to Bilinear CNN (B-CNN) (Qui et al., 2018) and can be used in any underwater applications to identify fish species and avoid misla-belling of seafood.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Fish play a prominent role in the food web and fish farming has value for both human consumption and tourist attractions.
📊
Key Findings & Data:In this research, we develop a new method by refining the squeeze and excitation network for the automatic fish species classification model to identify 23 different types of fish species.
💡
Conclusion & Impact:Then post-training with the small-scale dataset (Croatian) achieved an accuracy of 94.99% with an 11% improvement compared to Bilinear CNN (B-CNN) (Qui et al., 2018) and can be used in any underwater applications to identify fish species and avoid misla-belling of seafood.
🔬Design:Modeling & Simulation
📍Scope:2018 Verileri
⚙️Variables:Deep Learning · Convolutional Neural Network · Squeeze and Excitation

Abstract

Fish play a prominent role in the food web and fish farming has value for both human consumption and tourist attractions. Due to the increasing importance of marine biodiversity, recognition of fish species has become a prominent task in monitoring the mislabelling of seafood and extinct species. This problem can be solved using traditional manual annotation on the images. To reduce manpow-er, cost, and tremendous time, deep learning approaches are used which always require large data-sets. Therefore, fish species identification is a challenging task using disproportionately small data sets. In this research, we develop a new method by refining the squeeze and excitation network for the automatic fish species classification model to identify 23 different types of fish species. To achieve this, a hybrid framework using deep learning is proposed on a large-scale dataset and implemented transfer learning for a small-scale dataset. Deep learning methods can be used to identify fish in un-derwater images. In this study, we have proposed a new method of hybrid Deep Convolutional Neu-ral Network (CNN) along with a Support Vector Machine (SVM) for classification. Additionally, the Squeeze and Excitation (SE) block has been improved for improved feature extraction. The proposed method achieved an accuracy of 97.90%. Then post-training with the small-scale dataset (Croatian) achieved an accuracy of 94.99% with an 11% improvement compared to Bilinear CNN (B-CNN) (Qui et al., 2018) and can be used in any underwater applications to identify fish species and avoid misla-belling of seafood.

🔖

Cite This Article

VELUSWAMİ, J. R. S., P, N. (2022). Multi-species Fish Identification using Hybrid DeepCNN with Refined Squeeze and Excitation Architecture. Aquatic Sciences and Engineering, Cilt: 37 - Sayı: 4, 220–228. https://ajindex.com/articles/722867

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (3)

  1. Allken, V., Handegard, N. O., Rosen, S., Schreyeck, T., Mahiout, T., & Malde, K. (2019). Fish species identification using a convolutional neural network trained on synthetic data. ICES Journal of Marine Science, 76(1), 342-349. google scholar B. B. B. Phoenix X. Huang and R. B. Fishera.Fish4KnowledgeDataset: https://homepages.inf.ed.ac.uk/rbf/Fish4Knowledge/ GROUNDTRUTH/RECOG/. 2013. google scholar Chen, P. Y., Ho, C. W., Chen, A. C., Huang, C. Y., Liu, T. Y., & Liang, K. H. (2020). Inves-tigating seafood substitution problems and consequences in Taiwan using molecular barcoding and deep microbiome profiling. Scientific reports, 10(1), 1-9. google scholar Crozier, L. G., McClure, M. M., Beechie, T., Bograd, S. J., Boughton, D. A., Carr, M.,. & Willis-Norton, E. (2019). Climate vulnerability assessment for Pacific salmon and steelhead in the California Current Large Marine Ecosystem. PloS one, 14(7), e0217711. google scholar Dagoudo, M., Qiang, J., & Solevo, M. P. (2022). Status in science and technology devel- opments in Benin’s aquaculture industry: a review. Aquaculture International, 1-15. google scholar Data Science Glossary. https://c3.ai/glossary/data-science/. google scholar Deep, B. V., & Dash, R. (2019, March). Underwater fish species recognition using deep learning techniques. In 2019 6th International Conference on Signal Processing and Integrated Networks (SPIN) (pp. 665-669).
  2. IEEE. google scholar Dos Santos, A. A., & Goncalves, W. N. (2019). Improving Pantanal fish species recogni- tion through taxonomic ranks in convolutional neural networks. Ecological Informatics, 53, 100977. google scholar Du, J., Zhou, H., Qian, K., Tan, W., Zhang, Z., Gu, L., & Yu, Y. (2020). RGB-IR cross input and sub-pixel upsampling network for infrared image super-resolution. Sensors, 20(1), 281. google scholar Fouad, M. M. M., Zawbaa, H. M., El-Bendary, N., & Hassanien, A. E. (2013, December). Automatic nile tilapia fish classification approach using machine learning techniques. In 13th international conference on hybrid intelligent systems (HIS 2013) (pp. 173-178).
  3. IEEE. google scholar Hu, J., Shen, L., & Sun, G. (2018).’Squeeze-and-excitation networks.’ In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7132-7141). google scholar ImageNet Dataset. https://image-net.org/download.php. 2013. google scholar Jalal, A., Salman, A., Mian, A., Shortis, M., & Shafait, F. (2020). Fish detection and species classification in underwater e