Detecting Fake Faces In Smart Cities Security Surveillance Using Image Recognition And Convolutional Neural Networks

Abstract

Smart cities are planned to have millions of Internet-connected sensors and devices. Sensors can create a huge amount of data in a range of applications. In modern urban environments, quality of life in a Smart City is heavily dependent on the safety of its residents. For a long time, public safety has been a major source of anxiety. For everyone, stopping a breach of private space security has become a priority. Traditional security systems raise an alarm whenever they detect a breach of safety. It is possible to find a breach of an advanced model by using image processing and a deep analysis of convolutional neural networks to classify images. Because of the ability to reduce complicated aspects from photographs using exact algorithms for facial and body detection. The results of specific machine learning, such as deep learning techniques are outstanding. The processing time of the proposed system is reduced, and true rate of face recognition is 72.7% under varying distance from 2m to 5m.This paper aims to show that when used together the security sector, the two can achieve more than might have been previously assumed models.