Contactless access control system for critical objects based on deep learning neural networks

Abstract

The paper presents a software product that enables contactless identity verification at various sites using Leap Motion controller and neural network module, which will improve security at critical sites. The authors present the results of a study of numerical sequence generation for identification through two-factor authentication and a predictive hand model recognition module to perform automatic identification of an individual. The process of verification of an identifiable fingerprint is based on a decision support system–by means of a fuzzy rule base, the percentage coefficient of accessibility for an identifiable person is determined. In addition, the algorithm has been optimised to work with devices based on ARM single board computers-the deployment is in this case an independent customer authorisation unit at a remote distance from the information processing server with the varied possibility of working offline and online modes.