Central Europe faces an overabundance of wild ungulates, which is driven by several factors, including traditional hunting practices. The harvest of females is insufficient and recorded without verification, even when they were not actually hunted. This practice contributes to further population growth through accurate hunting records. Therefore, basic procedures for automated registration based on muzzle pattern animal biometric evaluation of harvested wild ungulates were proposed. The red deer ( Cervus elaphus ) served as the model species. For the assessment of biometric characteristics, 2,193 photographs were taken from the frontal and overhead directions of 972 harvested red deer during regular game management. A comparison of the collected images using the LoFTR ( Local Feature TRansformer ) method revealed the potential for individual identification, with the peak accuracy of 95.048%. On the contrary, the minimum accuracy was 90.048% using a combination of overhead and frontal images of high and medium quality. Because there is no solution for the recognition of ungulates the comparison of these results was performed with the recognition systems for pets and livestock. Achieved accuracy is around 2% better than comparable recognition systems (with similar dataset size, number of feature points, etc.). The results confirmed that biometric methods can be used to identify and record harvested game. This can be achieved by developing a mobile application that transmits images for automated comparison and evaluation. Once individual identity is confirmed, the animal will be registered. This ensures a verifiable record of harvested game and provides a solid foundation for sustainable hunting planning.
Kanich et al. (Tue,) studied this question.