This report describes a complete Face Recognition Attendance System based on AI. With this system, attendance will be taken automatically with the use of a camera and the latest technologies in Deep Learning. Currently, the traditional ways of taking attendance are limited by requiring large amounts of manual effort. The comprehensive AI-based Face Recognition Attendance System will offer a single integrated solution that includes: (i) Registration of a student's face, (ii) Capture of live attendance through a camera, (iii) Automatic marking of attendance, (iv) Generation of attendance reports, and (v) Providing verification logs. The Face Recognition Attendance System has a comprehensive architecture which consists of using Convolutional Neural Networks (CNN) as the method of facial feature extraction and facial recognition, while preventing duplicate entries and handling unknown faces. The technology stack used for developing the Face Recognition Attendance System consists of React for the user interface, Node.js for the API server, Python for the Deep Learning components, and MySQL for database management. The implementation of the Face Recognition Attendance System uses a number of common Python libraries, including: TensorFlow for training Deep Learning models, OpenCV for detecting faces and performing image processing, and NumPy for performing numerical calculations. The system can be divided into three main phases: (i) Detecting a face using Haar Cascade Classifiers, (ii) Recognising a face using trained CNN models, and (iii) Logging the recognition to a secure database with a time stamp. The results from the experiments conducted at the school demonstrate an overall recognition accuracy of 94.2% when students were attendance in a classroom setting. The results also indicate that the FBAS can effectively manage errors such as unknown faces and duplicates through time locks. The research supports the findings.
Face Recognition, Attendance Automation, Convolutional Neural Network, Deep Learning, Computer Vision, React, Node.js, Python, TensorFlow, OpenCV, MySQL
International Journal of Trend in Scientific Research and Development - IJTSRD having
online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International
Journal which provides rapid publication of your research articles and aims to promote
the theory and practice along with knowledge sharing between researchers, developers,
engineers, students, and practitioners working in and around the world in many areas
like Sciences, Technology, Innovation, Engineering, Agriculture, Management and
many more and it is recommended by all Universities, review articles and short communications
in all subjects. IJTSRD running an International Journal who are proving quality
publication of peer reviewed and refereed international journals from diverse fields
that emphasizes new research, development and their applications. IJTSRD provides
an online access to exchange your research work, technical notes & surveying results
among professionals throughout the world in e-journals. IJTSRD is a fastest growing
and dynamic professional organization. The aim of this organization is to provide
access not only to world class research resources, but through its professionals
aim to bring in a significant transformation in the real of open access journals
and online publishing.