Automated Identification of Deoni Cattle Using YOLOv5-Assisted Siamese Deep Learning Framework

V B Dongre

doi:10.56093/ijans.v96i5.175242

Authors

V B Dongre College of Veterinary and Animal Sciences, Udgir Dist-Latur (Maharashtra)

https://doi.org/10.56093/ijans.v96i5.175242

Keywords:

Breed Identification, Deoni cattle, Machine learning, YOLOv5

Abstract

Deoni cattle are one of the most important indigenous cattle breeds in India. Traditionally, their identification relies on visual inspection, a method that is subjective and highly prone to errors. The accuracy of breed identification can be significantly enhanced through the application of machine learning techniques. In this study, an automated system for Deoni cattle identification is developed using a deep learning framework that combines a Siamese network with YOLOv5 for effective feature extraction. A dataset comprising images of Deoni cattle and other breeds was used for model training and evaluation. The performance of the proposed framework was assessed using standard machine learning metrics, including precision–recall analysis and confusion matrices. The results demonstrate that machine learning–based approaches can provide accurate and reliable identification of Deoni cattle

Downloads

Download data is not yet available.

Author Biography

V B Dongre, College of Veterinary and Animal Sciences, Udgir Dist-Latur (Maharashtra)

Subject Matter Specialist (Animal Genetics & Breeding) Cattle Breeding Farm, College of Veterinary and Animal Sciences, Udgir Dist-Latur (Maharashtra)

References

Dong X, Shen J. 2021. Triplet loss in Siamese network for object tracking. Beijing Lab of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology; Inception Institute of Artificial Intelligence. 2021.

Dong X. and J. Shen. 2021. Triplet Loss in Siamese Network for Object Tracking. Beijing Lab of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, China, and Inception Institute of Artificial Intelligence, Abu Dhabi, UAE.

Dongre V. B., R. S. Gandhi, V. M. Salunke, L. S. Kokate, S. M. Durge, V. N. Khandait, and P. V. Patil. 2017. Present Status and Future Prospects of Deoni Cattle. Indian Journal of Animal Sciences, 87 (7):800–803.

Gupta H., P. Jindal, O. P. Verma, R. K. Arya, A. A. Ateya, N. F. Soliman, and V. Mohan. 2022. Computer Vision-Based Approach for Automatic Detection of Dairy Cow Breed. Electronics, 11(22): 3791.

Jogi R., G. Temburnikar, A. Jadhav, A. Biradar, S. Gajbhiv, and A. Malge. 2024. Cattle Breed Classification Techniques: Framework and Algorithm Evaluation. Journal of Propulsion Technology, 45(1): 1739–1745.

Khosla P., P. Teterwak, C. Wang, A. Sarna, Y. Tian, P. Isola, A. Maschinot, C. Liu, and D. Krishnan. 2020. Supervised Contrastive Learning. An Advances in Neural Information Processing Systems, 33: 18661–18673.

Kumar S. and S. K. Singh. 2020. Cattle recognition: A new frontier in visual animal biometrics research. Proceedings of the National Academy of Sciences, India Section A: Physical Sciences, 90(4): 689–708.

Porto J, Higa G, Weber V, Weber F, Loebens N, Claure P, de Almeida L, Porto K, Pistori H. 2024. A new Siamese network loss for cattle facial recognition in a few-shot learning scenario. AgriEngineering, 6(3): 2941–2954.

Porto J, Higa G, Weber V, Weber F, Loebens N, Claure P, de Almeida L, Porto K, Pistori H. 2024. A new Siamese network loss for cattle facial recognition in a few-shot learning scenario. AgriEngineering, 6(3):2941–2954.

Weber de Lima F., L. P. Magalh˜aes, D. R. A. Pereira, P. A. J. Monteiro, L. A. A. Pereira, L. F. S. Oliveira, and M. C. A. Salgado. 2020. Recognition of Pantaneira cattle breed using computer vision and convolutional neural networks. Computers and Electronics in Agriculture, 175, 105548.

Zhao C., H. Wang, Y. Zhang, Y. Zhao, and J. Gao. 2023. Breed identification using breed-informative SNPs and machine learning based on whole genome sequence data and SNP chip data. Journal of Animal Science and Biotechnology, 14(85)- 1–13.