Cattle identification based in biometric features of the muzzle

Cattle identification has been a serious issue for breeding association. The muzzle pattern that is correlated with human fingerprints has been considered as a biometric marker for cattle and could be used in identification of bovine animals. This work presents a robust and fast cattle identification scheme from muzzle images using Speed-up Robust Features matching. To eliminate miss-matched outliers a matching refinement technique based on the matching orientation information has been proposed