Comparison of Different Deep-Learning Methods for Image Classification

In this paper, we showed how to solve exemplary image classification problem. The goal of image classification problem is to correctly classify the input image within the expected class/label. In our case, we focused on classifying the animal image into one of two categories: mammals or birds. That classification problem is not a trivial task using standard machine learning algorithms. The main reason for that is the fact that the algorithms are based on previously prepared features for classifying object. It is often done by hand by a researcher. Defining specific features for example how a beak looks, wing, tail, fur and etc. is natural for humans, but understanding it by computers is extremely difficult. However, nowadays deep learning algorithms managed to overcome some obstacles and work best for these types of problems. We can use Deep Neural Networks (DNN) in two ways - by developing it from scratch for the specific problem or using method calls transfer learning. The main goal of this paper is comparing the two methods by using them in a real-life example. We showed how to correctly prepare a dataset, create a DNN model from scratch and how to adjust it. We also showed how to use the transfer learning technique. All the steps we made are described in a way which allows for easy adaptation of these algorithms to similar problems.