Recognition and classification of animals based on texture features through parallel computing

In this work, we proposed an efficient system for animal recognition and classification based on texture features which are obtained from the local appearance and texture of animals. The classification of animals are done by training and subsequently testing two different machine learning techniques, namely k-Nearest Neighbors (k-NN) and Support Vector Machines (SVM). Computer-assisted technique when applied through parallel computing makes the work efficient by reducing the time taken for the task of animal recognition and classification. Here we propose a parallel algorithm for the same. Experimentation is done for about 30 different classes of animals containing more than 3000 images. Among the different classifiers, k-Nearest Neighbor classifiers have achieved a better accuracy.