TurtleNet: Explainable Turtle Species Classification Using Attention-Enhanced EfficientNetB4 and Ensemble Learning

DOI: https://doi.org/10.52549/ijeei.v14i2.7994
Published: 22-06-2026 • Issue: Vol. 14 No. 2: June 2026 • Section: Regular paper

Abstract

Turtles are remarkable organisms as they play a vital role in maintaining a balanced and healthy ecosystem. However, their existence is at risk due to growing threats of habitat loss, illegal trade and environmental degradation. To support conservation and monitoring efforts for these turtle species, this study proposes TurtleNet, a custom deep learning model designed to accurately identify turtle species with acute precision. The proposed model relies on a customized EfficientNetB4 architecture as a backbone with an enhanced lightweight attention mechanism of Squeeze and Excitation blocks, allowing it to focus on subtle visual features that distinguish closely related species. The model was trained and evaluated on our curated Turtle1 dataset as well as the images.cv turtle dataset. The performance comparison of TurtleNet with 11 individual state-of-the-art deep learning classification models showed its superior ability by classifying Asian turtle species with 97.25% accuracy. To further enhance classification performance, TurtleNet is integrated with the YOLOv8 model using a soft-voting ensemble strategy, thereby increasing the classification accuracy by 2.41%. The results demonstrate that TurtleNet has strong potential for automated species monitoring and conservation using non-invasive measures. Grad-CAM visualization is used to highlight discriminative morphological regions relevant to image identification and is used to interpret the feature selection process of the proposed model.

References

A. G. J. Rhodin et al., “Global Conservation Status of Turtles and Tortoises (Order Testudines),†Chelonian Conservation and Biology, vol. 17, no. 2, p. 135, Dec. 2018, doi: 10.2744/CCB-1348.1.

H. Nagashima, S. Kuraku, K. Uchida, Y. Kawashima-Ohya, Y. Narita, and S. Kuratani, “Body plan of turtles: an anatomical, developmental and evolutionary perspective,†Anat Sci Int, vol. 87, no. 1, pp. 1–13, Mar. 2012, doi: 10.1007/s12565-011-0121-y.

S. Singh, S. Badola, and M. Fernandes, “The Identification (ID) Cards: Tortoises and Freshwater Turtles of India.†TRAFFIC, India Office, 2023. Accessed: Feb. 23, 2025. [Online]. Available: https://wwfin.awsassets.panda.org/downloads/tortoise_and_freshwater_turtles_id_cards__2023.pdf

J. Wyneken, K. J. Lohmann, and J. A. Musick, Eds., “- Predators, Prey, and the Ecological Roles of Sea Turtles,†in The Biology of Sea Turtles, Volume III, 0 ed., CRC Press, 2013, pp. 268–303. doi: 10.1201/b13895-15.

R. Faurina, A. Wijanarko, A. F. Heryuanti, S. I. Ishak, and I. Agustian, “Comparative study of ensemble deep learning models to determine the classification of turtle species,†Comput. Sci. Inf. Technol., vol. 4, no. 1, pp. 24–32, Mar. 2023, doi: 10.11591/csit.v4i1.p24-32.

J.-W. Baek, J.-I. Kim, and C.-B. Kim, “Deep learning-based image classification of sea turtles using object detection and instance segmentation models,†PLoS ONE, vol. 19, no. 11, p. e0313323, Nov. 2024, doi: 10.1371/journal.pone.0313323.

J.-W. Baek, J.-I. Kim, and C.-B. Kim, “Deep learning-based image classification of turtles imported into Korea,†Sci Rep, vol. 13, no. 1, p. 21677, Dec. 2023, doi: 10.1038/s41598-023-49022-3.

P. Sukyen, K. Chuiad, and P. Chaisiriprasert, “Sea Turtles Species Classification With a Modified ResNet-50 Deep Learning Model,†in 2024 8th International Conference on Information Technology (InCIT), Chonburi, Thailand: IEEE, Nov. 2024, pp. 554–559. doi: 10.1109/InCIT63192.2024.10810619.

W. Songpan, T. Chaianunporn, K. Lomthaisong, and S. Keithmaleesatti, “Automated classification in turtles genus Malayemys using ensemble multiview image based on improved YOLOv8 with CNN,†Sci Rep, vol. 14, no. 1, p. 24993, Oct. 2024, doi: 10.1038/s41598-024-76431-9.

J. Liu, M. Wang, L. Bao, X. Li, J. Sun, and Y. Ming, “Classification and Recognition of Turtle Images Based on Convolutional Neural Network,†IOP Conf. Ser.: Mater. Sci. Eng., vol. 782, no. 5, p. 052044, Mar. 2020, doi: 10.1088/1757-899X/782/5/052044.

W. R. Da Paixao, T. M. Paixao, M. C. B. Da Costa, J. O. Andrade, F. G. Pereira, and K. S. Komati, “Texture Classification of Sea Turtle Shell Based on Color Features: Color Histograms and Chromaticity Moments,†IJAIA, vol. 9, no. 2, pp. 55–67, Mar. 2018, doi: 10.5121/ijaia.2018.9205.

U. Mendiratta, V. Sheel, and S. Singh, “Enforcement seizures reveal large-scale illegal trade in India’s tortoises and freshwater turtles,†Biological Conservation, vol. 207, pp. 100–105, Mar. 2017, doi: 10.1016/j.biocon.2017.01.023.

C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,†2015, arXiv. doi: 10.48550/ARXIV.1512.00567.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,†2015, arXiv. doi: 10.48550/ARXIV.1512.03385.

A. Howard et al., “Searching for MobileNetV3,†2019, arXiv. doi: 10.48550/ARXIV.1905.02244.

Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, “A ConvNet for the 2020s,†2022, arXiv. doi: 10.48550/ARXIV.2201.03545.

G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely Connected Convolutional Networks,†2016, arXiv. doi: 10.48550/ARXIV.1608.06993.

K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,†2014, arXiv. doi: 10.48550/ARXIV.1409.1556.

R. Varghese and S. M., “YOLOv8: A Novel Object Detection Algorithm with Enhanced Performance and Robustness,†in 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), Chennai, India: IEEE, Apr. 2024, pp. 1–6. doi: 10.1109/ADICS58448.2024.10533619.

D. Yuehua and P. Huilin, “Improved garbage image classification for inception-Resnet-V2,†in 2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML), Hangzhou, China: IEEE, Mar. 2022, pp. 477–481. doi: 10.1109/CACML55074.2022.00087.

F. Chollet, “Xception: Deep Learning with Depthwise Separable Convolutions,†2016, arXiv. doi: 10.48550/ARXIV.1610.02357.

image.cv, “Sea turtle Labeled Image Dataset.†image.cv, Sea turtle. Accessed: Feb. 12, 2025. [Jpg]. Available: https://images.cv/dataset/sea-turtle-image-classification-dataset

A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,†in Advances in Neural Information Processing Systems, F. Pereira, C. J. Burges, L. Bottou, and K. Q. Weinberger, Eds., Curran Associates, Inc., 2012. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf

C.-Y. Zhu et al., “A Deep Learning Based Framework for Diagnosing Multiple Skin Diseases in a Clinical Environment,†Front. Med., vol. 8, p. 626369, Apr. 2021, doi: 10.3389/fmed.2021.626369.

J. Hu, L. Shen, and G. Sun, “Squeeze-and-Excitation Networks,†in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT: IEEE, Jun. 2018, pp. 7132–7141. doi: 10.1109/CVPR.2018.00745.

A. Mohammed and R. Kora, “A comprehensive review on ensemble deep learning: Opportunities and challenges,†Journal of King Saud University - Computer and Information Sciences, vol. 35, no. 2, pp. 757–774, Feb. 2023, doi: 10.1016/j.jksuci.2023.01.014.

J. Jareño, G. Bárcena-González, J. Castro-Gutiérrez, R. Cabrera-Castro, and P. L. Galindo, “Automatic labeling of fish species using deep learning across different classification strategies,†Front. Comput. Sci., vol. 6, p. 1326452, Feb. 2024, doi: 10.3389/fcomp.2024.1326452.

Author Biographies

Pragyat Jyoti Baruah
Research Scholar, Department of Computer Science and Engineering.
Bugge Prince Solomon Raj Kumar
B.Tech. Student, Department of Computer Science and Engineering.
Arun Jyoti Nath
Department of Ecology and Environmental Science, Rank: Professor.
Arnab Paul
Department of Computer Science and Engineering, Rank: Assistant Professor.
Jarine Anjum
B.Tech. Student, Department of Computer Science and Engineering.
Akash Nath
B.Tech. Student, Department of Computer Science and Engineering.
Tirthanka Borah
Research Scholar, Department of Computer Science and Engineering.

How to Cite

[1]
P. J. Baruah et al., “TurtleNet: Explainable Turtle Species Classification Using Attention-Enhanced EfficientNetB4 and Ensemble Learning”, IJEEI, vol. 14, no. 2, pp. 533–547, Jun. 2026, doi: 10.52549/ijeei.v14i2.7994.