期刊名称:International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN:2320-9798
电子版ISSN:2320-9801
出版年度:2021
卷号:9
期号:7
页码:8336-8341
DOI:10.15680/IJIRCCE.2021.0907084
语种:English
出版社:S&S Publications
摘要:This project presents a security bot that performs facial recognition using Internet of Things (IoT), controlled via an Android application for examining threats in its vicinity. The bot is capable of detecting humans in real time scenarios. The project cycle of the robot is classified in a number of tasks: Face Detection, Face Recognition, generation of alerting to the user. The bot detects the human face based on CNN using a camera module interfaced with Raspberry Pi. The structure is exposed to numerous facial images of people from distinct angles and background conditions. This forms the data collection to train the system which aids in facial recognition. Subsequently, when the bot detects a human face, it initiates the algorithm for recognition of face which uses Convolutional Neural Network (CNN) approach. According to images in the dataset, the bot determines whether the human detected is a threat or not. In case of a match with the dataset, the user receives a message through Twilio module on his/her mobile phone along with the name of the person recognized. In case of a irreconcilable, a threat or an alert message is received by the user. The motion of the bot is controlled by the android application.