An Intelligent Informative Totem Application Based on Deep CNN in Edge Regime

Giammatteo, PaoloValente, GiacomoD'Ortenzio, AlessandroIn this paper we present an application targeting an informative totem, with a discussion about its possible usage and the requirements it needs to satisfy. In this regard, we propose a Machine Learning algorithm, a Convolutional Neural Network, performing computation on images taken from a camera on an edge-computing platform. Performance tests on two different edge processors are reported, respectively for a CPU and a GPU, and a comparison with the principal competitors is provided. Our final goal is to lay the foundation for the application of an informative totem in an edge computing regime, which is able to recognize the age and the gender of the person approaching it in order to give a better presentation of its contents.