Auto Fish: Leveraging AI for fish species identification in natural habitats

Neha Bora; Rajendra S. Chaudhari; Monika P. Surse; Rajendra C. Patil; Pradyumna Mulchand Bora

doi:10.29194/NJES.29010131

Authors

Neha Bora Department of Computer Engineering,‎ SNJB’s Late Sau. K. B. Jain, College of Engineering, Chandwad, Dist. Nashik, Maharashtra, India.
Rajendra S. Chaudhari Department of Mechanical Engineering,‎ SNJB’s Late Sau. K. B. Jain, College of Engineering, Chandwad, Dist. Nashik, Maharashtra, India.
Monika P. Surse Department of Computer Engineering,‎ SNJB’s Late Sau. K. B. Jain, College of Engineering, Chandwad, Dist. Nashik, Maharashtra, India.
Rajendra C. Patil Department of Mechanical Engineering,‎ SNJB’s Late Sau. K. B. Jain, College of Engineering, Chandwad, Dist. Nashik, Maharashtra, India.
Pradyumna Mulchand Bora Department of Mechanical Engineering,‎ SNJB’s Late Sau. K. B. Jain, College of Engineering, Chandwad, Dist. Nashik, Maharashtra, India.

DOI:

https://doi.org/10.29194/NJES.29010131

Keywords:

Deep Learning, MobileNetV2, Fish Species Identification, Tensorflow Lite, Ecological Monitoring, Real-Time Classification

Abstract

Identifying fish species in natural aquatic environments remains challenging due to changing light conditions, turbid water, and complex underwater scenes. Most current deep-learning models rely on controlled datasets, which limits their use in real-world settings. This study presents Auto Fish, a mobile deep-learning system for real-time, offline fish species identification on Android devices. The system uses the MobileNetV2 architecture, optimized with TensorFlow Lite for processing on the device. This approach ensures high accuracy while keeping computational costs low. We trained and evaluated the model on a balanced dataset of 8,000 annotated images, including nine marine species: Sea bass, Red sea bream, Horse mackerel, Gilt-head bream, Shrimp, Black sea sprat, Trout, Red mullet, and Striped red mullet. Extensive preprocessing, image enhancement, and stratified sampling helped the model perform well despite variations in lighting and background conditions. The experimental results showed a validation accuracy of 99.2%, with both macro and micro Precision, Recall, and F1-scores around 99.3%, and an average False Positive Rate (FPR) of 0.09%. The system supports offline recognition, cloud syncing via Firebase, and delivers real-time results within 4.2 seconds per image on mid-range smartphones. These findings show that Auto Fish can effectively classify fish species in the field while remaining efficient and easy to use. This work offers a practical AI-based solution that connects research with ecological monitoring, empowering citizen scientists and conservationists to document biodiversity using mobile technology.

Downloads

Download data is not yet available.

References

H. T. Rauf, M. I. U. Lali, S. Zahoor, S. Z. H. Shah, A. Ur Rehman, and S. A. C. Bukhari, "Visual features based automated identification of fish species using deep convolutional neural networks," Comput. Electron. Agric., vol. 167, p. 105075, 2019.

https://doi.org/10.1016/j.compag.2019.105075 DOI: https://doi.org/10.1016/j.compag.2019.105075

K. V. Uma, T. J. Priya, L. R. Jenneyl, and S. S. Srilakshmi, "Deep learning approaches for automated fish species identification," Mach. Intell. Res., vol. 18, no. 2, pp. 85-101, Aug. 2024.

N. B. M. Kumar, "Automated fish species identification using deep learning models: A comprehensive study," J. Soft Comput. Comput. Intell., vol. 2, no. 1, pp. 8-20, 2025.

A. Suryavanshi, V. Kukreja, A. Dogra, P. Aggarwal, and M. Manwal, "FishNet: A hybrid deep learning and machine learning framework for precise fish species identification," in Proc. 11th Int. Conf. Signal Process. Integrated Netw. (SPIN), Noida, India, 2024, pp. 221-226.

https://doi.org/10.1109/SPIN60856.2024.10511360 DOI: https://doi.org/10.1109/SPIN60856.2024.10511360

I. M. Yusup, M. Iqbal, and I. Jaya, "Real-time reef fishes identification using deep learning," IOP Conf. Ser.: Earth Environ. Sci., vol. 429, no. 1, p. 012046, Jan. 2020.

https://doi.org/10.1088/1755-1315/429/1/012046 DOI: https://doi.org/10.1088/1755-1315/429/1/012046

F. Kurniawan, G. B. Satrya, and F. Kamalov, "Lightweight fish classification model for sustainable marine management: Indonesian case," arXiv preprint, arXiv:2401.02278, 2024.

D. Siri, G. Vellaturi, S. H. Shaik Ibrahim, S. Molugu, V. S. Desanamukula, R. Kocherla, and R. Vatambeti, "Enhanced deep learning models for automatic fish species identification in underwater imagery," Heliyon, vol. 10, no. 15, p. e35217, Jul. 2024.

https://doi.org/10.1016/j.heliyon.2024.e35217 DOI: https://doi.org/10.1016/j.heliyon.2024.e35217

J. G. A. Barbedo, "A review on the use of computer vision and artificial intelligence for fish recognition, monitoring, and management," Fishes, vol. 7, no. 6, p. 335, 2022.

https://doi.org/10.3390/fishes7060335 DOI: https://doi.org/10.3390/fishes7060335

A. Mohammadisabet, R. Hasan, V. Dattana, S. Mahmood, and S. Hussain, "CNN-based optimization for fish species classification: Tackling environmental variability, class imbalance, and real-time constraints," Information, vol. 16, no. 2, p. 154, 2025.

https://doi.org/10.3390/info16020154 DOI: https://doi.org/10.3390/info16020154

J. Murugaiyan, M. Palaniappan, T. Durairaj, and V. Muthukumar, "Fish species recognition using transfer learning techniques," Int. J. Adv. Intell. Informatics, vol. 7, no. 2, pp. 188-197, 2021.

https://doi.org/10.26555/ijain.v7i2.610 DOI: https://doi.org/10.26555/ijain.v7i2.610

O. Ulucan, D. Karakaya, and M. Turkan, "A large-scale dataset for fish segmentation and classification," in Proc. Innovations Intell. Syst. Appl. Conf. (ASYU), Istanbul, Turkey, 2020, pp. 1-5.

https://doi.org/10.1109/ASYU50717.2020.9259867 DOI: https://doi.org/10.1109/ASYU50717.2020.9259867

S. Villon, D. Mouillot, M. Chaumont, E. S. Darling, G. Subsol, T. Claverie, and S. Villéger, "A deep learning method for accurate and fast identification of coral reef fishes in underwater images," Ecol. Informatics, vol. 48, pp. 238-244, 2018.

https://doi.org/10.1016/j.ecoinf.2018.09.007 DOI: https://doi.org/10.1016/j.ecoinf.2018.09.007

K. S. Mehrab et al., "Fish-Vista: A multi-purpose dataset for understanding and identification of traits from images," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Nashville, TN, USA, 2025, pp. 24275-24285.

https://doi.org/10.1109/CVPR52734.2025.02261 DOI: https://doi.org/10.1109/CVPR52734.2025.02261

G. F. Garcia, T. Corpetti, M. Nevoux et al., "AcousticIA, a deep neural network for multi-species fish detection using multiple models of acoustic cameras," Aquat. Ecol., vol. 57, pp. 881-893, 2023.

https://doi.org/10.1007/s10452-023-10004-2 DOI: https://doi.org/10.1007/s10452-023-10004-2

X. Yang, S. Zhang, J. Liu, Q. Gao, S. Dong, and C. Zhou, "Deep learning for smart fish farming: Applications, opportunities and challenges," Rev. Aquacult., vol. 13, pp. 66-90, 2021.

https://doi.org/10.1111/raq.12464 DOI: https://doi.org/10.1111/raq.12464

Z. Ju and Y. Xue, "Fish species recognition using an improved AlexNet model," Optik, vol. 223, p. 165499, 2020.

https://doi.org/10.1016/j.ijleo.2020.165499 DOI: https://doi.org/10.1016/j.ijleo.2020.165499

J. M. V. D. B. Jayasundara, R. M. L. S. Ramanayake, H. M. N. B. Senarath, H. M. S. L. Herath, G. M. R. I. Godaliyadda, M. P. B. Ekanayake, H. M. V. R. Herath, and S. Ariyawansa, "Deep learning for automated fish grading," J. Agric. Food Res., vol. 14, p. 100711, 2023.

https://doi.org/10.1016/j.jafr.2023.100711 DOI: https://doi.org/10.1016/j.jafr.2023.100711

A. Salman, A. Jalal, F. Shafait, A. Mian, M. Shortis, J. Seager, and E. Harvey, "Fish species classification in unconstrained underwater environments based on deep learning," Limnol. Oceanogr.: Methods, vol. 14, pp. 570-585, 2016.

https://doi.org/10.1002/lom3.10113 DOI: https://doi.org/10.1002/lom3.10113

E. Prasetyo, N. Suciati, and C. Fatichah, "Multi-level residual network VGGNet for fish species classification," J. King Saud Univ.-Comput. Inf. Sci., vol. 34, no. 8, pp. 5286-5295, 2022.

https://doi.org/10.1016/j.jksuci.2021.05.015 DOI: https://doi.org/10.1016/j.jksuci.2021.05.015

Kaggle, "A large-scale fish dataset," Kaggle Datasets, 2020.

M. Tan and Q. V. Le, "EfficientNet: Rethinking model scaling for convolutional neural networks," in Proc. 36th Int. Conf. Mach. Learn. (ICML), 2019, pp. 6105-6114.

X. Zhang, X. Zhou, M. Lin, and J. Sun, "ShuffleNet: An extremely efficient convolutional neural network for mobile devices," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Salt Lake City, UT, USA, 2018, pp. 6848-6856.

https://doi.org/10.1109/CVPR.2018.00716 DOI: https://doi.org/10.1109/CVPR.2018.00716

N. Gunawardena, J. A. Ginige, B. Javadi, and G. Lui, "Performance analysis of CNN models for mobile device eye tracking with edge computing," Procedia Comput. Sci., vol. 207, pp. 2291-2300, 2022.

https://doi.org/10.1016/j.procs.2022.09.288 DOI: https://doi.org/10.1016/j.procs.2022.09.288