Home Security System Using RaspberryPi

Abstract

AbstractWith the development of advanced technologies in the field of robotics and computer vision, real time image processing has become a very popular tool. The paper aims at using the RaspberryPi camera along with suitable machine learning algorithms to perform face detection and face recognition for security purpose. This paper portrays machine-learning approach for face recognition with high identification rates using Intel’s open source framework called OpenCV (Open Source Computer Vision) library in python programming language. RaspberryPi-cam is used to capture picture of the faces that are to be stored in the database in the form of grayscale and colored image. This is a three-stage process namely, face detection, data gathering, and face recognition, which will match the live faces with facial pictures stored in the database and give us identification details of the person under consideration. If the matching index is 45% or more then only the face will be recognized properly. Here, Haar-Cascade algorithm is used and this whole setup is successfully demonstrated using a RaspberryPi model 3B hardware setup. Based on successful face recognition, a miniature door will open and the security of the system will be ensured. Whereas, if the face matching index is below the threshold, then the face is not to be identified and the door will remain closed. This is a real-time implementation of smart security application using RaspberryPi.KeywordsOpenCVRaspberry PiFace recognitionHaar-Cascade algorithm