AI-based face recognition system with telegram notification for room security on raspberry PI

Abstract

This research is based on the importance of a security system in a room by implementing AI combined with the telegram notification system. The goal is that security information can be obtained quickly and in real-time. The methodology used is to design a hardware system consisting of input, process and output devices. The input device consists of a Logitech C270 camera mounted on 2 MG966R type servo motors so that the camera can rotate on the X and Y axes, then the results of the camera captures are processed using the Haar Cascade Classifier and Local Binary Pattern Histogram (LBPH) algorithms. Raspberry Pi 4 is used as a data processing center and push notification to telegrams in the form of images when faces are detected by a web camera. Only registered users may enter the room, by opening the door when a face is recognized. Our findings show that a room security system with an AI-based facial recognition application can be implemented, according to the planning and design results in this study. The door opening process produces an average result of 4.586 seconds, with the longest time being 4.981 seconds and the fastest time being 4.116 seconds. The door closing process produces an average result of 4.496 seconds, with the longest time being 4.966 seconds and the fastest time being 4.106 seconds. The average time of opening and closing the door is ideal and safe. From the results of the research that has been done, it can be concluded that the use of AI in this study aims to make decisions that only registered users can enter a room. In addition, the ability of the camera to move dynamically on the x and y axes is one of the system developments that did not exist before, so that the ability to take pictures besides being more accurate also becomes wider dynamic.