Articles | Volume 68, issue 3
https://doi.org/10.5194/aab-68-473-2025
https://doi.org/10.5194/aab-68-473-2025
Original study
 | 
14 Jul 2025
Original study |  | 14 Jul 2025

Deep-learning-based buffalo identification through muzzle pattern images

Orhan Ermetin and Humar Kahramanlı Örnek

Related authors

Evaluation of the application opportunities of precision livestock farming (PLF) for water buffalo (Bubalus bubalis) breeding: SWOT analysis
Orhan Ermetin
Arch. Anim. Breed., 66, 41–50, https://doi.org/10.5194/aab-66-41-2023,https://doi.org/10.5194/aab-66-41-2023, 2023
Short summary

Related subject area

Husbandry
On-farm welfare assessment of semi-extensively managed sheep using Animal Welfare Indicators (AWIN) protocol
Serdar Koçak, Zehra Bozkurt, Özlem Gücüyener Hacan, Koray Çelikeloğlu, Mustafa Tekerli, Mustafa Demirtaş, Samet Çinkaya, and Metin Erdoğan
Arch. Anim. Breed., 68, 459–472, https://doi.org/10.5194/aab-68-459-2025,https://doi.org/10.5194/aab-68-459-2025, 2025
Short summary
Comparison of some economic traits by genetic cluster of Aberdeen Angus cattle
Judit Márton, Szabolcs Bene, István Anton, Attila Zsolnai, and Ferenc Szabó
Arch. Anim. Breed., 68, 279–286, https://doi.org/10.5194/aab-68-279-2025,https://doi.org/10.5194/aab-68-279-2025, 2025
Short summary
The effect of litter hierarchy and teat allocation on suckling piglets' growth
Fernando Mata, José Araújo, Alicja Kowalczky, and Joaquim Cerqueira
Arch. Anim. Breed., 68, 263–269, https://doi.org/10.5194/aab-68-263-2025,https://doi.org/10.5194/aab-68-263-2025, 2025
Short summary
Agreement of the morphometric dimensions determined by traditional and image analysis methods for Arabian and Thoroughbred horses
Necmettin Ünal, Yavuzkan Paksoy, and Ömer Faruk Güngör
Arch. Anim. Breed., 68, 253–261, https://doi.org/10.5194/aab-68-253-2025,https://doi.org/10.5194/aab-68-253-2025, 2025
Short summary
Effects of birth weight and growth traits on the first lactation milk yield and reproduction characteristics in Anatolian buffaloes
Sinem Akçam and Ertuğrul Kul
Arch. Anim. Breed., 68, 193–199, https://doi.org/10.5194/aab-68-193-2025,https://doi.org/10.5194/aab-68-193-2025, 2025
Short summary

Cited articles

Andrew, W., Greatwood, C., and Burghardt, T.: Aerial animal biometrics: Individual friesian cattle recovery and visual identification via an autonomous uav with onboard deep inference, in: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), November 2019, 237–243, IEEE, 2019. 
Awad, A. I.: From classical methods to animal biometrics: A review on cattle identification and tracking, Comput. Electron. Agr., 123, 423–435, https://doi.org/10.1007/s00500-022-06935-x, 2016. 
Awad, A. I., Hassanien, A. E., and Zawbaa, H. M. A.: Cattle identification approach using live captured muzzle print images, in: International Conference on Security of Information and Communication Networks 2013, September, 143–152, Berlin, Heidelberg, Springer, https://doi.org/10.1007/978-3-642-40597-6, 2013. 
Balagourouchetty, L., Pragatheeswaran, J. K., Pottakkat, B., and Ramkumar, G.: GoogLeNet-based ensemble FCNet classifier for focal liver lesion diagnosis, IEEE J. Biomed. Health, 24, 1686–1694, https://doi.org/10.1109/JBHI.2019.2942774, 2019. 
Baranov, A. S., Graml, R., Pirchner, F., and Schmid, D. O.: Breed differences and intra-breed genetic variability of dermatoglyphic pattern of cattle, J. Anim. Breed. Gen., 110, 385–392, https://doi.org/10.1111/j.1439-0388.1993.tb00751.x, 1993. 
Short summary

The study utilises artificial intelligence to improve buffalo recognition in livestock management. It employs facial images of 11 buffaloes to develop a dataset and utilises four CNN (convolutional neural network) algorithms to identify buffaloes based on muzzle patterns. Results indicate successful performance, with SqueezeNet achieving the highest accuracy of 99.88 %, along with high precision, recall, and F1 score.

Share