International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 3, pp. 162-168, March 2026.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Image-based Animal Type Classification for Cattle and Buffaloes
K Bhaskar
G Yamuna
Maratis Thorani
J Nithin Kumar Reddy
N Rahul
K V Yatin
Department of ECE, Siddartha Institute of Science and Technology, Puttur, Andhra Pradesh, India
Abstract: This paper aims to automatically identify whether an animal in an image is cattle or a buffalo using deep learning. The system follows a step-by-step process that includes collecting images, cleaning and preparing them, and creating more training samples through augmentation. Two powerful models, EfficientNetV2-M and Vision Transformer, are trained separately to learn different types of features from the images. Their outputs are then combined using an attention fusion method, and the result is produced through an ensemble prediction that improves accuracy. The system is tested using standard evaluation measures, showing that the combined model performs better than individual models. This approach provides a fast, low-cost, and reliable solution for smart livestock identification.
Keywords: EfficientNetV2-M, Vision Transformer, Attention Fusion, Ensemble Learning, Image Classification.
References:
- Vasagam, S. N. Vasagam and M. Sornam, “Species Wise Classification of Crust Leather images based on histogram equalization,” 2022 6th International Conference on Computing Methodologies and Communication (ICCMC), Erode, India, 2022, pp. 1307-1312, doi: 10.1109/ICCMC53470.2022.9753704.
- D. W. Girmaw, “Livestock animal skin disease detection and classification using deep learning approaches,” Biomedical Signal Processing and Control, vol. 102, p. 107334, Dec. 2024, doi: 10.1016/j.bspc.2024.107334.
- C. V. Patil et al., “A database of dentition images of Indian breed cattle and estimation of cattle’s age using deep learning algorithms,” Engineering Applications of Artificial Intelligence, vol. 162, p. 112172, Oct. 2025, doi: 10.1016/j.engappai.2025.112172.
- M. Chu, Y. Si, Q. Li, X. Liu, and G. Liu, “Deep learning-based model to classify mastitis in Holstein dairy cows,” Biosystems Engineering, vol. 252, pp. 92–104, Mar. 2025, doi: 10.1016/j.biosystemseng.2025.02.013.
- A. I. Awad, “From classical methods to animal biometrics: A review on cattle identification and tracking,” Computers and Electronics in Agriculture, vol. 123, pp. 423–435, Mar. 2016, doi: 10.1016/j.compag.2016.03.014.
- H. Meng et al., “Livestock Biometrics Identification Using Computer Vision Approaches: A review,” Agriculture, vol. 15, no. 1, p. 102, Jan. 2025, doi: 10.3390/agriculture15010102.
- T. Lee, Y. Na, B. G. Kim, S. Lee, and Y. Choi, “Identification of Individual Hanwoo Cattle by Muzzle Pattern Images through Deep Learning,” Animals, vol. 13, no. 18, p. 2856, Sep. 2023, doi: 10.3390/ani13182856.
- H. Gupta et al., “Computer Vision-Based Approach for Automatic Detection of Dairy cow breed,” Electronics, vol. 11, no. 22, p. 3791, Nov. 2022, doi: 10.3390/electronics11223791.
- Y. Pan, H. Jin, J. Gao, and H. Rauf, “Identification of buffalo breeds using Self-Activated-Based improved convolutional neural networks,” Agriculture, vol. 12, no. 9, p. 1386, Sep. 2022, doi: 10.3390/agriculture12091386.
- S. L. Mon, T. Onizuka, P. Tin, M. Aikawa, I. Kobayashi, and T. T. Zin, “AI-enhanced real-time cattle identification system through tracking across various environments,” Scientific Reports, vol. 14, no. 1, p. 17779, Aug. 2024, doi: 10.1038/s41598-024-68418-3.
- P. N, L. K, N. K. D, S. S. M, Y. K. S, and Y. S, “Image based breed identification for cattle and buffaloes of India,” SSRN Electronic Journal, Jan. 2026, doi: 10.2139/ssrn.6404249.
- D. Li, B. Li, Q. Li, Y. Wang, M. Yang, and M. Han, “Cattle identification based on multiple feature decision layer fusion,” Scientific Reports, vol. 14, no. 1, p. 26631, Nov. 2024, doi: 10.1038/s41598-024-76718-x.
- Y. Zhang, L. Colli, and J. S. F. Barker, “Asian water buffalo: domestication, history and genetics,” Animal Genetics, vol. 51, no. 2, pp. 177–191, Jan. 2020, doi: 10.1111/age.12911.