Short-Term Longitudinal Biometric Identification of Cattle Using Planum Nasolabiale Images and a Two-Stage Deep Learning Framework

Selahattin Ozan Yardımcı, İmdat Orhan, Fatih İsmail Bahar · 2026

Read Short-Term Longitudinal Biometric Identification of Cattle Using Planum Nasolabiale Images and a Two-Stage Deep Learning Framework by Selahattin Ozan Yardımcı, İmdat Orhan, Fatih İsmail Bahar (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13611888.txt.

Description

Selahattin Yardımcı and co-authors test whether a cow's muzzle print can identify it months later. Ear tags and other markers can be lost or damaged, but the nose pattern is unique and can be photographed without touching the animal. Their system works in two stages: one model finds the muzzle in a photo, and a second names the animal. They photographed 48 cattle, cows and calves, twice about four and a half months apart, taking four shots each time.

The finder model, trained on separate slaughterhouse and public photos, located every muzzle in its test sets with high scores. Photos from the second visit were kept aside as a fresh test, and the system named the right animal 96.3 percent of the time, answering in about eight milliseconds per photo. Growing calves were included and still matched well.

Catalog record

CREATORSelahattin Ozan Yardımcı, İmdat Orhan, Fatih İsmail Bahar
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE25 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13611888

Browse the full library · About the Tower of Babel