DOI:
https://doi.org/10.64539/sjcs.v2i2.2026.463Keywords:
Snakes, Classification, Deep Learning, Image Data, Long Short-Term MemoryAbstract
Snakes are a major health threat in various communities, specifically where human and snake encounters are frequent. When a snake is not identified correctly, healthcare providers often administer the wrong treatment, this can worsen patient recovery outcomes or even prove fatal to the victim. Therefore, a fast, proper and accurate distinction between venomous and nonvenomous snakes is vital for proper antivenom administration. This study proposes a hybrid deep learning system combining a CNN and an LSTM model for snake image classification through feature extraction from visual data. The CNN extracts key spatial features such as colour and scale patterns, texture, and body shape, whereas the LSTM captures sequential dependencies across these features, by helping distinguish visual similarity amongst the species. The model was trained and evaluated on a dataset of 6,798 snake images from diverse sources. The system achieved a performance of 97% accuracy, 97% precision, 96% recall, an F1-score of 97%, and a ROC-AUC of 0.97. These results demonstrate that integrating CNN and LSTM is moderately effective for snake classification. The proposed system has practical applications in the area of emergency healthcare, wildlife management, as well as mobile based identification tool. With 97% accuracy, this model can improve emergency responders first aid, enhance a safer treatment administration and help make safer decisions on the use of antivenom, by reducing treatment delays and improving patient survival prognosis. This model has the potential to save lives and minimize the consequences of snakebite envenoming.
References
[1] World Health Organization, “Snakebite envenoming,” Fact sheet, Geneva, Switzerland: WHO, Sep. 2024. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/snakebite-envenoming.
[2] World Health Organization, “Control of Neglected Tropical Diseases,” 2023, [Online]. Available: https://www.who.int/teams/control-of-neglected-tropical-diseases/snakebite-envenoming/prevalence. Accessed: Sep. 10, 2024.
[3] M. J. Mazerolle, L. L. Bailey, W. L. Kendall, J. A. Royle, S. J. Converse, and J. D. Nichols, “Making great leaps forward: accounting for detectability in herpetological field studies” Journal of Herpetology, vol. 41, no. 4, pp. 672-689, 2007. https://www.jstor.org/stable/40060463.
[4] Walk Through India, “India’s 10 Beautiful but Deadliest Venomous Snakes,” 2021. [Online]. Available: https://www.walkthroughindia.com/wildlife/indias-10-beautiful-but-deadliest-venomous-snakes. Accessed: Sep. 15, 2024.
[5] I. Bolon, L. Picek, A. M. Durso, G. Alcoba, F. Chappuis, and R. Ruiz de Castañeda, “An artificial intelligence model to identify snakes from across the world: Opportunities and challenges for global health and herpetology,” PLoS Neglected Tropical Diseases, vol. 16, no. 8, p. e0010647, 2022. https://doi.org/10.1371/journal.pntd.0010647.
[6] N. I. Progga, N. Rezoana, M. S. Hossain, R. U. Islam, and K. Andersson, “A CNN based model for venomous and non-venomous snake classification,” in Applied Intelligence and Informatics: Proc. AII 2021, Nottingham, U.K., Jul. 2021, pp. 216–231. https://doi.org/10.1007/978-3-030-82269-9_17.
[7] M. Rajabizadeh and M. Rezghi, “A comparative study on image-based snake identification using machine learning,” Scientific Reports, vol. 11, no. 1, p. art. No. 19142, 2021. https://doi.org/10.1038/s41598-021-96031-1.
[8] P. Joshi, S. Sati, T. Choudhury, T. Bajaj, K. Kotecha, A. Sar, “Classification of Venomous and Non-venomous Snakes Using Transfer Learning with MobileNetV2.” in International Conference on Universal Threats in Expert Applications and Solutions, vol 1006, pp 427–438, 2024. https://doi.org/10.1007/978-981-97-3810-6_35.
[9] K. Ahmed, M. A. Gad, and A. E. Aboutabl, “Snake species classification using deep learning techniques,” Multimedia Tools and Applications, vol. 83, no. 12, pp. 35117–35158, 2024. https://doi.org/10.1007/s11042-023-16773-0.
[10] S. Anwarul and R. Tanwar, “Venomify: Automated classification of venomous and non-venomous snake species using deep learning,” Procedia Computer Science, vol. 259, pp. 219–229, 2025. https://doi.org/10.1016/j.procs.2025.03.323.
[11] S. Anwarul, T. Misra, and D. Srivastava, “An IoT & AI-assisted framework for agriculture automation” In 2022 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), 2022. https://doi.org/10.1109/ICRITO56286.2022.9964567.
[12] A. P. James, B. Mathews, S. Sugathan, and D. K. Raveendran, “Discriminative histogram taxonomy features for snake species identification.” Human-centric Computing and Information Sciences, vol. 4, no. 1, pp. 1–11, 2014. https://doi.org/10.1186/s13673-014-0003-0.
[13] V. Patel, A. Chudasama, and A. Thakkar, “YOLOv11 Based Classification of Lumbar Spine Degenerative Changes Across Multi-Modal Imaging.” in AIJR Proceedings, vol. 7, no. 6, pp. 7–18, 2025. https://doi.org/10.21467/proceedings.7.6.2
[14] S. B. Islam, D. Valles, and M. R. J. Forstner, “Herpetofauna Species Classification from Images with Deep Neural Network.” In 2020 Intermountain Engineering, Technology and Computing (IETC), pp. 1-6, 2020. https://doi.org/10.1109/IETC47856.2020.9249141.
[15] I. S. Abdurrazaq, S. Suyanto, and D. Q. Utama, “Image-based classification of snake species using convolutional neural network.” In 2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), pp. 97–102. IEEE, 2019. https://doi.org/10.1109/ISRITI48646.2019.9034633.
[16] R. Kamalraj, “Deep learning model for identifying snakes by using snakes’ bite marks” In 2020 International Conference on Computer Communication and Informatics (ICCCI), pp. 1-4. IEEE, 2020. https://doi.org/10.1109/ICCCI48352.2020.9104200.
[17] L. Jeantet and E. Dufourq, “Improving deep learning acoustic classifiers with contextual information for wildlife monitoring,” Ecological Informatics, vol. 77, 102256, 2023. https://doi.org/10.1016/j.ecoinf.2023.102256.
[18] D. Lakshmi, R. C. Panda, Amrita, and A. Prakash, “Life-Saving APP: Snake Classification ‘Venomous and Nonvenomous’ Using fast. ai Based on Indian Species” In European, Asian, Middle Eastern, North African Conference on Management & Information Systems, pp. 109-115, 2021. https://doi.org/10.1007/978-3-030-77246-8_11.
[19] S. B. Abayaratne, W. M. K. S. Ilmini, and T. G. I. Fernando, “Automated methods to identify snake species in Sri Lanka: A review,” Scholar Bank Library, University of Sri Jayewardenepura, 2019. http://dr.lib.sjp.ac.lk/handle/123456789/12078.
[20] S. Anwarul, “An efficient minimum spanning tree-based color image segmentation approach,” in International Advanced Computing Conference, Cham, Switzerland: Springer International Publishing, 2021, pp. 588–598. https://doi.org/10.1007/978-3-030-95502-1_44.
[21] C. Shorten and T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” Journal of Big Data, vol. 6, no. 1, 2019. https://doi.org/10.1186/s40537-019-0197-0.
[22] L. Arcila-Díaz, H. Mejía-Cabrera, and J. Arcila-Díaz, “Estimation of mango fruit production using image analysis and machine learning algorithms,” Informatics, vol. 11, no. 4, p. 87, 2024. https://doi.org/10.3390/informatics11040087.
