A Deep Learning based Approach for Real Time Face Recognition System

Face recognition technology provides us with a wide range of possibilities for creating a safe and secure environment. In this paper, two separate approaches are applied mutually while designing a hybrid solution for face identification. The MTCNN method is applied to the real-time video frame produced by the security camera. Moreover, a deep learning-based approach was used to generate the facial landmarks from the obtain face images, and the model was trained using the Res-Net architecture. Furthermore, MongoDB is used as a database to store the facial landmarks and corresponding identity, and if the system cannot identify the person, an alarm is generated, and an auto-generated message immediately sends to the owner's email address. This way it creates a strong security system.