No CrossRef data available.
Article contents
Deep learning assisted muzzle-based identification of Vrindavani cattle – A crossbred of India
Published online by Cambridge University Press: 15 October 2025
Abstract
Biometric identification represents a transformative, advanced technology with significant implications for herd management. Its adoption addresses the critical requirement of accurate identification methods along with upgraded approaches on higher traceability, disease control, genetic management, and economic returns. In this work, a database of muzzle images was collected from 264 Vrindavani cattle, with ages ranging from 6 months to 10 years. To assess the accuracy of muzzle print as a biometric means of identification, this study investigated the efficiency of a 68-layer convolutional neural network called SqueezeNet for the identification of Vrindavani cattle (a crossbred developed in India) using 2,640 muzzle images. It was observed that SqueezeNet gives a harmonious blend of superior accuracy and minimal complexity, rendering it an optimal option for devices with constrained specifications and computing power. Further, the results of this study showed an identification accuracy of 97.22% with a remarkably small model size (<4 MB). This compact size makes it significantly advantageous compared to other models.
Information
- Type
- Research Article
- Information
- Copyright
- © The Author(s), 2025. Published by Cambridge University Press on behalf of Hannah Dairy Research Foundation.
References
Bara, S, Singh, M, Pandey, HO, Chauhan, A, Gaur, GK, Pandey, AK and Das, A (2024) Machine learning-based prediction of cattle body weight using muzzle morphometrics. Journal of Scientific Research & Reports 30, 670–677.10.9734/jsrr/2024/v30i82288CrossRefGoogle Scholar
Byeon, H, Raina, V, Sandhu, M, Shabaz, M, Keshta, I, Soni, M and Matrouk, K (2024) Artificial intelligence-enabled deep learning model for multimodal biometric fusion. Multimedia Tools and Applications 83(33), 80105–80128.Google Scholar
Cihan, P, Saygılı, A, Ermutlu, ÇŞ, 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 226, 109391.CrossRefGoogle Scholar
Cihan, P, Saygili, A, Ozmen, NE and Akyuzlu, M (2023) Identification and recognition of animals from biometric markers using computer vision approaches: a review. Kafkas Universitesi Veteriner Fakultesi Dergisi 29(6), 581–593.Google Scholar
Girish, PS, Santhosh, K, Kartikeya, K, Palekar, P, Harikrishna, CH and Rathod, S (2020) Artificial intelligence-based muzzle recognition technology for individual identification of animals. Indian Journal of Animal Science 90, 1070–1073.10.56093/ijans.v90i7.106684CrossRefGoogle Scholar
Hitelman, A, Edan, Y, Godo, A, Berenstein, R, Lepar, J and Halachmi, I (2022) Biometric identification of sheep via a machine-vision system. Computers and Electronics in Agriculture 194, 106713.10.1016/j.compag.2022.106713CrossRefGoogle Scholar
Jiang, HH, Li, B, Ma, Y, Bai, SY, Dahmer, TD, Linacre, A and Xu, YC (2020) Forensic validation of a panel of 12 SNPs for identification of Mongolian wolf and dog. Scientific Reports 10, 13249.10.1038/s41598-020-70225-5CrossRefGoogle ScholarPubMed
Kimani, GN, 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 arXiv:2311.08148.Google Scholar
Kosana, V, Gunda, VSP and Kosana, V (2022) ADEEC- multistage novel framework for cattle identification using muzzle prints. In Second International Conference on Computer Science, Engineering and Applications (ICCSEA), Gunupur, India, 1–6.10.1109/ICCSEA54677.2022.9936195CrossRefGoogle Scholar
Kumar, S, Pandey, A, Satwik, K, Kumar, S, Singh, SK, Singh, AK and Mohan, A (2018) Deep learning framework for recognition of cattle using muzzle point image pattern. Measurement 116, 1–17.10.1016/j.measurement.2017.10.064CrossRefGoogle Scholar
Kumar, S and Singh, SK (2016) Automatic identification of cattle using muzzle point pattern: a hybrid feature extraction and classification paradigm. Multimedia Tools and Applications 76, 26551–26580.CrossRefGoogle Scholar
Kumar, S and Singh, SK (2020) Cattle recognition: a new frontier in visual animal biometrics research. Proceedings of the National Academy of Sciences, India Section A: Physical Sciences 90, 689–708.CrossRefGoogle Scholar
Kumar, S, Singh, SK and Singh, AK (2017) Muzzle point pattern-based techniques for individual cattle identification. IET Image Processing 11, 805–814.CrossRefGoogle Scholar
Kusakunniran, W and Chaiviroonjaroen, T (2018) Automatic Cattle Identification based on Multi-Channel LBP on Muzzle Images. In International Conference on Sustainable Information Engineering and Technology (SIET), Malang, Indonesia, 1–5.Google Scholar
Mahato, S and Neethirajan, S (2024) Integrating artificial intelligence in dairy farm management-biometric facial recognition for cows. Information Processing in Agriculture. doi:10.1016/j.inpa.2024.10.001CrossRefGoogle Scholar
Minagawa, H, Fujimura, T, Ichiyanagi, M and Tanaka, K (2002) Identification of beef cattle by analyzing images of their muzzle patterns lifted on paper. In AFITA 2002: Asian Agricultural Information Technology & Management. Proceedings of the Third Asian Conference for Information Technology in Agriculture, Beijing, China, 26–28 October 2002, China Agricultural ScienceTech Press, 596–600.Google Scholar
Roy, S, Mukherjee, K, Nath Mandal, S, Hajra, DK, Banik, S and Naskar, S (2021) Black Bengal goat identification using iris images. In: Proceedings of International Conference on Frontiers in Computing and Systems: COMSYS 2020, Springer Singapore, 213–224.10.1007/978-981-15-7834-2_20CrossRefGoogle Scholar
Ruiz-Garcia, L and Lunadei, L (2011) The role of RFID in agriculture: applications, limitations and challenges. Computers and Electronics in Agriculture 79, 42–50.Google Scholar
Saygılı, A, Cihan, P, Ermutlu, ÇŞ, Aydın, U and Aksoy, Ö (2024) CattNIS: novel identification system of cattle with retinal images based on feature matching method. Computers and Electronics in Agriculture 221, 108963.10.1016/j.compag.2024.108963CrossRefGoogle Scholar
Singh, P, Devi, KJ and Varish, N (2021) Muzzle pattern-based cattle identification using generative adversarial networks. In Soft Computing for Problem Solving: Proceedings of SocProS, Springer Singapore, 1, 13–23.10.1007/978-981-16-2709-5_2CrossRefGoogle Scholar
Smink, M, Liu, H, Döpfer, D and Lee, YJ (2024) Computer Vision on the Edge: individual Cattle Identification in Real-Time with ReadMyCow System. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 7056–7065.Google Scholar
Tharwat, A, Gaber, T, Hassanien, AE, Hassanien, HA and Tolba, MF (2014) Cattle identification using muzzle print images based on texture features approach. In Proceedings of the Fifth International Conference on Innovations in Bio-Inspired Computing and Applications (IBICA), Springer International Publishing, 217–227.10.1007/978-3-319-08156-4_22CrossRefGoogle Scholar