What the study found
The study found that muzzle-pattern biometrics, which use the unique pattern on an animal’s snout, can identify harvested red deer with high accuracy. The authors report peak identification accuracy of 95.048%.
Why the authors say this matters
The authors say this matters because harvested female ungulates are sometimes recorded without verification, and this can affect hunting records. They conclude that automated biometric registration could provide a verifiable record of harvested game and support sustainable hunting planning.
What the researchers tested
The researchers proposed basic procedures for automated registration based on muzzle-pattern biometric evaluation of harvested wild ungulates, using red deer as the model species. They collected 2,193 photographs from frontal and overhead directions of 972 harvested red deer during regular game management and compared the images using the LoFTR (Local Feature TRansformer) method.
What worked and what didn't
The image comparisons showed a potential for individual identification. The highest reported accuracy was 95.048%, while the lowest was 90.048% using a combination of overhead and frontal images of high and medium quality. The authors also state that the achieved accuracy was around 2% better than comparable recognition systems for pets and livestock with similar dataset size and feature-point counts.
What to keep in mind
The abstract does not describe detailed limitations beyond noting that no existing ungulate recognition solution was available for comparison. The study used red deer as a model species, so the findings are presented in that context.
Key points
- Muzzle-pattern biometrics were reported to identify harvested red deer with peak accuracy of 95.048%.
- The study used 2,193 photographs from 972 harvested red deer.
- The LoFTR method was used to compare frontal and overhead images.
- The authors say the approach could support verifiable records of harvested game.
- The study notes that comparable recognition systems for pets and livestock were about 2% lower in accuracy.
Disclosure
- Research title:
- Muzzle-pattern biometrics identified harvested red deer accurately
- Authors:
- Ondřej Kanich, Jan Cukor, Jana Adámková, Vlastimil Skoták, Martin Sakin, Veronika Olejníčková, Tomáš Volf, Martin Drahanský, Vlastimil Hart
- Institutions:
- Czech University of Life Sciences Prague, Czech University of Life Sciences Prague, Czech University of Life Sciences Prague, Forestry and Game Management Research Institute, Forestry and Game Management Research Institute, Masaryk University, Masaryk University, Masaryk University, Masaryk University, Masaryk University
- Publication date:
- 2026-02-24
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with peer-reviewed research without reading academic papers — one filtered digest, every Friday.