Analytical Study of Hybrid Features and Classifiers for Cattle Identification

Abstract

Animals biometric identification system is emerging in pattern recognition and machine learning due to its diversification of applications and its uses nowadays. This new standard has received more attention due to its biometric features for identification of cattle. In this article, the authors have observed three feature extraction techniques that are Scale Invariant Feature Transform (SIFT), Speeded up Robust Feature (SURF) and Oriented Fast and rotated BRIEF (ORB) from the collected dataset. The classifiers, i.e., decision tree, k-NN, and random forest identify breed of cattle based on efficacy of extracted features. Experimental results are conducted on a dataset with accuracy of 97.23%.