Convolutional Neural Network with SVM for Classification of Animal Images

Advances in GPU, parallel computing, and deep neural network made rapid growth in the field of machine learning and computer vision. In this paper, we try to explore the convolution neural network to classify animals. The convolution neural network is a powerful machine learning tool which is trained using a large collection of diverse images. In this paper, we combine convolutional neural network and SVM for classification of animals. The animal images are trained using AlexNet pretrained convolution neural network. Further, the extracted features are fed into multiclass SVM classifier for the purpose of classification. To evaluate the performance of our system, we have conducted extensive experimentation on our own dataset of 5000 images with 50 classes, each class containing 100 images. From the results, we can easily observe that the proposed method has achieved a good classification rate compared to the works in the literature.