A face recognition-based automatic door access control system is developed to provide a more robust, secure, and less error-prone alternative to traditional methods such as keys, passwords, and ID cards. The system uses machine learning and artificial intelligence implemented on a Raspberry Pi 4, combined with a camera module, servo motor, and GSM module, to capture, train, and recognize users’ faces and control door actuation. Authorized users’ facial images are collected under various poses and lighting conditions and stored in a database; during operation, new captures are compared against this dataset to either grant access by unlocking the door or deny access while sending an SMS alert to a designated phone number. A prototype building was constructed to integrate all hardware components and demonstrate the access control process. Testing with fifty users showed that all were correctly granted access under proper illumination and pose, while some users were denied under poor lighting and pose variation, highlighting the system’s sensitivity to environmental and user-related factors.
@article{a054f00f-2366-4a6c-8e50-fdb592816167,
title={eversvd,+03 (4)},
author={Unknown},
year={2026},
language={en}
}TY - JOUR TI - eversvd,+03 (4) AU - Unknown PY - 2026 LA - en ER -
Mudila Dhanunjaya Rao, Kamalesh K. Singh
Rapid global technological development has resulted in increased production of electronic waste, which presents both challenges and opportunities in r
Roger Rumbu
This paper addresses the challenge of assessing the feasibility of wind power plant projects at sites with insufficient or no local historic wind data
Important advances in electrochemical engineering technology over the last three decades have fostered the development of a lternative methods to alle