What the study found
The study found that muzzle pattern biometrics can be used to identify harvested wild ungulates, with red deer used as the model species. The authors report that automated comparison of photographs reached a peak identification accuracy of 95.048%.
Why the authors say this matters
The authors conclude that verified identification of harvested game could help create a more reliable record of hunting. They say this provides a basis for sustainable hunting planning.
What the researchers tested
The researchers examined biometric characteristics from 2,193 photographs of 972 harvested red deer taken during regular game management. They compared frontal and overhead images using the LoFTR, or Local Feature TRansformer, method.
What worked and what didn't
The comparison showed a peak accuracy of 95.048%. The lowest reported accuracy was 90.048%, based on a combination of overhead and frontal images of high and medium quality. The authors also state that the results were about 2% better than comparable recognition systems for pets and livestock.
What to keep in mind
The abstract presents red deer as a model species, so the findings are described within that scope. It also does not provide detailed limitations beyond noting that no existing ungulate recognition solution was available for comparison.
- Red deer were used as the model species for testing muzzle pattern biometrics.
- The study analyzed 2,193 photographs from 972 harvested red deer.
- The LoFTR method produced a peak identification accuracy of 95.048%.
- The lowest reported accuracy was 90.048% with certain image-quality combinations.
- The authors say automated image comparison could support verifiable harvest records.