Senior Design Project Facial Recognition Using Machine Learning

Journal Title
Journal Title
Journal ISSN
Volume Title
Nowadays facial recognition strategy is a widely used method for authentication in the fast-growing digital world. Due to the advancement of machine learning algorithms, facial recognition has become the most effective, trusted, and more popular than fingerprint or any other authentication method. It is now also widely used for video surveillance or detecting any specific actions. Therefore, the industry is heavily investing more and more funds in this technology. Besides that, face recognition has a wide range of applications in fields such as intelligent security and access control, biometrics, safeguarding, verification, attendance accounting, and machine vision, among others. Face recognition has a lot of advantages over other technologies for determining a person’s personality: there is no need to physically meet the person, which is the most appropriate method for mass applications, and there is no need for specialized or expensive equipment. The difficulty of recognizing and identifying a person’s face using convolutional neural networks that process frames from a camera in real time or from a recorded video file, followed by the entry of the recognized individual into a database is discussed in this article. The Multitasking Cascade Convolutional Neural Network (MTCNN) is made up of three convolutional networks (P-Net, R-Net, and O-Net) that can surpass numerous face identification tests while preserving real-time performance. The proposed method for human face recognition was implemented as a software product, tested, and shown to have a 96.02% chance of being correct in real time.
TECHNOLOGY::Electrical engineering, electronics and photonics::Electrical engineering
Department Name
Electrical and Computer Engineering
North South University
Printed Thesis