Ar-powered educational application based upon convolutional neural network
O M Gushchina, A V Ochepovsky, Natalia Rogova, Anna Pupykina · Journal of Physics Conference Series · 2019
Abstract This research aims to justify the importance of using convolutional neural networks (CNN) in AR-powered educational applications to provide the learning process with impressive visualization of studied objects. Demonstration of the developed application proves neural network to be its basic part that allows for high-quality accuracy of object localization and image recognition in AR systems. As these systems provide a more informative and impressive way of learning, the application can be used for data mining and big data analysis disciplines to demonstrate real-time operation of localization, clustering and segmentation algorithms.