AI-Powered Cattle Identification Using Retinal Biometrics for Precision Livestock Farming
Keywords:
cattle Identification, Retinal Biometrics, Deep learning, Convolutional neural network, Generative adversarial network, Precision livestock farming, Biometric authenticationAbstract
Purpose: Conventional cattle identification methods such as ear tagging, branding, and radio-frequency identification (RFID) implants are physically invasive, prone to tag loss and tampering, and carry infection risk. The purpose of this study is to develop and test a unique, lifetime-stable cattle identification system based on artificial intelligence, non-contact, tamper-proof, vascular pattern of the bovine retina as a biometric identifier.
Design/methodology/approach: retinal fundus images of 10 individually labelled cattle were taken from a Kaggle repository and processed through four stages: green channel extraction, CLAHE, Gaussian denoising, and morphological filtering. After training a class-conditional Style-GAN2-ADA network to generate extra retinal images, an EfficientNetV2-S backbone network with Squeeze-and-Excitation (SE) attention blocks was trained in two steps: first, the backbone network was frozen and warmed up, and then it was fine-tuned using cosine annealing warm re-starts and tested using test-time augmentation.
Findings: On a held-out test set the proposed CNN+StyleGAN2 system achieved 99.90% accuracy, 99.90% weighted precision, 99.90% weighted recall, a 99.90% F1-score and 99.97% specificity, exceeding the state-of-the-art benchmark of 95.00% (Cihan et al., 2025) by 4.90 points and substantially outperforming classical baselines (K-Means 62.40%; SVM 81.70%), with ~23 ms inference and an 87 MB model footprint.
Originality: This work is one of the first to use the class-conditioned StyleGAN2-ADA augmentation along with SE-attention-enhanced EfficientNetV2-S for the biometrics of bovine retina, which is a scalable and humane solution to remove the need for physical tagging in precision live-stock farming.
References
Ahmad, M., Abbas, S., Fatima, A., Ghazal, T. M., Alharbi, M., Khan, M. A. and Elmitwally, N. S. (2023), "AI-Driven livestock identification and insurance management system", Egyptian Informatics Journal, Vol. 24 No. 3, pp. 100390.
Allen, A., Golden, B., Taylor, M., Patterson, D., Henriksen, D. and Skuce, R. (2008), "Evaluation of retinal imaging technology for the biometric identification of bovine animals in Northern Ireland", Livestock Science, Vol. 116 No. 1, pp. 42-52.
Bara, S., Das, A., Singh, M., Pandey, H. O., Gaur, G. K., Pandey, A. K., Narwal, S. and Tarafdar, A. (2025), "Deep learning assisted muzzle-based identification of Vrindavani cattle – A crossbred of India", Journal of Dairy Research, Vol. 92 No. 2, pp. 167-173.
Chowdhury, F., Galib, S. M., Adnan, M. N., Siddique, M. M., Karim, M. R. and Anjum, K. M. T. (2026), "Advanced Machine Learning and Deep Learning Techniques for Enhanced Cattle Identification and Detection: A Comprehensive Review", Annals of Emerging Technologies in Computing, Vol. 10 No. 2.
Cihan, P., Saygılı, A., Akyüzlü, M., Özmen, N. E., Ermutlu, C. Ş., Aydın, U., Yılmaz, A. and Aksoy, Ö. (2025), "Performance of machine learning methods for cattle identification and recognition from retinal images", Applied Intelligence, Vol. 55 No. 7, pp. 536.
Cihan, P., Saygılı, A., Şahin Ermutlu, C., Aydın, U. and Aksoy, Ö. (2024), "AI-aided cardiovascular disease diagnosis in cattle from retinal images: Machine learning vs. deep learning models", Computers and Electronics in Agriculture, Vol. 226, pp. 109391.
Ermetin, O. and Örnek, H. K. (2025), "Deep-learning-based buffalo identification through muzzle pattern images", Arch. Anim. Breed., Vol. 68 No. 3, pp. 473-484.
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y. (2014), "Generative adversarial nets", Advances in neural information processing systems, Vol. 27.
Han, M., Li, B., Li, Q., Wang, Y., Yang, M. and Gao, C. (2026), "Enhanced cattle identification using Siamese network and MobileViT with EMA attention", Frontiers in Veterinary Science, Vol. Volume 12 - 2025.
Hu, J., Shen, L. and Sun, G. (2018), "Squeeze-and-excitation networks", in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7132-7141.
Kang, M.-H. and Oh, S.-H. (2025), "Research trends in livestock facial identification: a review", Journal of Animal Science and Technology, Vol. 67 No. 1, pp. 43-55.
Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J. and Aila, T. (2020), "Training generative adversarial networks with limited data", Advances in neural information processing systems, Vol. 33, pp. 12104-12114.
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J. and Aila, T. (2020), "Analyzing and improving the image quality of stylegan", in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 8107-8116.
Kimani, G., Oluwadara, P., Fashingabo, P., Busogi, M., Luhanga, E., Sowon, K. and Chacha, L. (2023), "Cattle identification using muzzle images and deep learning techniques", arXiv preprint.
Kofa, J. N., Li, G., Dongbo, E. K., Li, S. and Li, J. (2026), "CattleBioNet: Multi-modal biometric identification system with adaptive fusion for cattle recognition", Smart Agricultural Technology, Vol. 14, pp. 102266.
Luthra, M., Sharma, M. and Chaudhary, P. (2025), "Cattle Identification and Detection using Vision Transformers and YOLOv8", Journal of Information Systems Engineering, Vol. 10 No. 42s, pp. 504-518.
Pathak, P. D. and Prakash, S. (2025), "Attention-based multi-modal robust cattle identification technique using deep learning", Computers and Electronics in Agriculture, Vol. 238, pp. 110747.
Pereira, E., Í, A., Silva, L. F. V., Batista, M., Júnior, S., Barboza, E., Santos, E., Gomes, F., Fraga, I. T., Davanso, R., Santos, D. O. d. and Nascimento, J. d. A. (2023), "RFID Technology for Animal Tracking: A Survey", IEEE Journal of Radio Frequency Identification, Vol. 7, pp. 609-620.
Saygılı, A., Cihan, P., Akyüzlü, M., Özmen, N. E., Ermutlu, C. Ş., Aydın, U., Yılmaz, A. and Aksoy, Ö. (2024), "Extraction of Cattle Retinal Vascular Patterns with Different Segmentation Methods", Sakarya University Journal of Computer and Information Sciences, Vol. 7 No. 3, pp. 378-388.
Tan, M. and Le, Q. (2021), "Efficientnetv2: Smaller models and faster training", in International conference on machine learning. PMLR, pp. 10096-10106.
Downloads
Published
License
Copyright (c) 2026 Hamda Wishal, Dr. Syed Mushhad Mustuzhar Gillani, Dr. Qamar Nawaz, Dr. Akmal Rehan (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
