Advanced ATM Robbery Prevention using Neural Network and IoT Technologies

Abstract

The basic idea behind the project is to develop a system which is automated and provides the most advanced security features in places like ATM. The project aims to give access to ATM’s for only those who follow the rules of the ATM usage that is preventing access to ATM for those wearing helmet. CNN (Convolutional Neural Network) Algorithm is used for identification like carrying any weapon, wearing helmet and mask identifications. Weapon detection using Tensor Flow increases the safety of ATM users and also increases the safety to the machine itself. In addition to the present, security to the machine is provided using a vibration sensor that is used to detect the movement of the machine just in case machine theft or Broken. Upon detection of the theft, the siren will begin alerting the public and door will be closed. Within the ATM chamber, the Solenoid valve is employed to leak the gas (Chloroform) to hold the thief into the unconscious stage. In addition to this, features like buzzer and alert notification to relevant security personnel is provided to enhance the security. The stepper motor controls the opening and closing of the ATM door. With help of above-mentioned attributes, law enforcement department authorities can guess the person involved in crime scene. And those suspected person images are captured, who are carrying weapons in an ATM, sent by mail to the authorized person respectively.