Smart Surveillance System Using Face and Optical Character Recognition for Secure Environment

Abstract

One of the important applications in the smart surveillance system is to identify unknown suspicious persons. Instead of manually and tediously monitoring the cameras continuously, this system can be used to identify and recognize suspected individuals and consequently send a warning message on the occurrence of such recognition. In this work, we propose a novel methodology, in which the system is connected to a database containing images of the Aadhar cards of the malfunctioning individuals. Since SQL database cannot directly store images, the Aadhar card pictures will have to be stored in a NoSQL database. The proposed system was built utilizing the Python language and the PyCharm IDE. The input video stream is processed frame by frame using the OpenCV library. The system will process each frame to check for the presence of a face. If a face is found, it matches the detected face with each of the faces present in the Aadhar card photos stored in the connected database. This process is carried out using a face recognition algorithm. If a match is found, the system uses OCR to isolate and recognize the text present in the image in order to get the name and Aadhar card number of the offender, and subsequently an alert will be displayed to the corresponding moderators with the name and Aadhar card number of that individual, in order to facilitate the necessary action.