Cattle Identification Based on Muzzle Images Using Gabor Features and SVM Classifier

Abstract

The accuracy of animal identification plays an important role for producers to make management decisions about their individual animal or about their complete herd. The animal identification is also important to animal traceability systems as ensure the integrity of the food chain. Usually, recording and reading of tags-based systems are used to identify animal, but only effective in eradication programs of national disease. Recently, animal biometric-based solutions, e.g. muzzle imaging system, offer an effective and secure, and rapid method of addressing the requirements of animal identification and traceability systems. In this paper, we propose a robust and fast cattle identification through using Gabor filter-based feature extraction method. We extract Gabor features from three different scales of muzzle print images. SVM classifier with its different kernels (Gaussian, Polynomial, Linear and Sigmoid) has been applied to Gabor features. Also, two different levels of fusion are used namely feature fusion and classifier fusion. The experimental results showed that Gaussian-based SVM classifier has achieved the best accuracy among all other kernels and generally our approach is superior than existed works as ours achieves 99.5% identification accuracy. In addition, the identification rate when the fusion is done at the feature level is better than that is done at classification level.