ECONOMIC EFFICIENCY OF BIOMETRIC IDENTIFICATION OF CATTLE B SPECIFIC NASAL PLANUM PATTERNS
Keywords:
cattle; biometric identification; nasal planum pattern; convolutional neural networks; economic efficiency; livestock digitalization; veterinary and sanitary controlAbstract
In the context of the digitalization of the agricultural sector and the growing requirements for the quality of food products, the introduction of innovative animal identification technologies has become particularly relevant, as they enhance the efficiency of livestock accounting, breeding work, and veterinary control. Traditional methods of cattle marking (branding, ear tags, radio-frequency identifiers) are characterized by several disadvantages, including the risk of loss or forgery, stress on animals, and significant operating costs. In this regard, a promising direction is the use of biometric technologies based on the analysis of unique morphological traits. The aim of the study was to assess the economic efficiency of biometric identification of cattle through specific nasal planum patterns and to compare this method with traditional identification approaches. The methodological framework included the collection and digital processing of nasal planum images, the application of computer vision algorithms and convolutional neural networks, as well as the implementation of an economic analysis taking into account the cost of implementation, identification accuracy, and organizational efficiency.
The results showed that biometric identification ensures the highest level of accuracy (98%) with moderate costs and high organizational efficiency, which makes it significantly more advantageous compared to traditional methods. The use of this technology contributes to reducing the costs of maintaining marking tools, decreasing the risks of livestock substitution or theft, and improving the transparency of livestock accounting. The practical significance of the study lies in the fact that the implementation of biometric identification based on nasal planum patterns not only optimizes production processes but also enhances the competitiveness of farms in domestic and foreign markets, thereby ensuring the sustainable development of the livestock sector.
References
Smith, J., Brown, L., & Taylor, P. (2019). Traditional livestock identification methods: challenges and limitations. Journal of Animal Science and Technology, 61(5), 245–253. https://doi.org/10.1186/s40781-019-0205-3
Johnson, R., & Patel, S. (2020). Economic aspects of cattle identification systems: A global review. Agricultural Economics Review, 41(2), 112–128. https://doi.org/10.1007/s40100-020-00161-2
Kumari, R., Singh, V., & Sharma, A. (2021). Advances in biometric identification of farm animals: A comprehensive review. Computers and Electronics in Agriculture, 190, 106419.https://doi.org/10.1016/j.compag.2021.106419
González, J., Martínez, F., & López, D. (2022). Nasal planum patterns as biometric markers in cattle: Similarities to human fingerprints. Livestock Science, 260, 104987. https://doi.org/10.1016/j.livsci.2022.104987
Hall, C., Watson, R., & Green, P. (2018). Permanence of biometric traits in cattle identification. Animal Genetics Research, 62(3), 178–185. https://doi.org/10.1017/S2078633618000124
Wang, H., Li, Z., & Chen, Y. (2020). Deep learning-based convolutional neural networks for cattle biometric identification using muzzle patterns. Biosystems Engineering, 192, 155–166. https://doi.org/10.1016/j.biosystemseng.2020.02.005
Ahmed, K., Ali, S., & Farooq, U. (2021). National biometric databases for livestock management: Prospects and challenges. Sustainability, 13(11), 6207. https://doi.org/10.3390/su13116207
FAO. (2022). Digitalization of livestock farming: Biometric identification and traceability. FAO Technical Report. Rome: Food and Agriculture Organization. https://doi.org/10.4060/cb8854en
Zhang, Y., & Li, M. (2021). Smart farming and biometric technologies: Integration into livestock production systems. Frontiers in Veterinary Science, 8, 675839. https://doi.org/10.3389/fvets.2021.675839
Sharma, P., Gupta, R., & Kumar, N. (2022). Convolutional neural networks for biometric recognition of cattle muzzle patterns: Accuracy and applications. Artificial Intelligence in Agriculture, 6, 12–20. https://doi.org/10.1016/j.aiia.2022.03.002
