Innovative Animal Identification Model usingCNN–Based Multi–Classification

Due to the randomness in the image characteristics, especially for the animal breeds, automated classification of animal images is a difficult task. Both public and private sectors have invested a vast amount of money in percent years to conserve the ecosystem and to spread the endangered numerous animal species in their natural habitats. This research work deals with the identification of individual animals based on image classification, using pre-trained deep convolutional networks. The accuracy of the model is evaluated using standard classification metrics namely Accuracy, Precision, Recall, and F1-score.