DESIGN AND CONSTRUCTION OF DOOR ACCESS CONTROL SYSTEM USING FACIAL RECOGNITION
Abstract
The project “Design And Construction Door Access Control System Using Facial Recognition” focuses on developing a facial recognition–based door access control system using the ESP32-CAM, which has a built-in camera and Wi-Fi. The system captures live images and identifies users by comparing detected faces with a stored database.
When an authorized face is recognized, a relay module unlocks the motorized door, while an LED provides status feedback. Features such as adjustable unlocking duration, error handling, and remote notifications enhance usability and reliability.
Testing showed that the system performs well under normal lighting and offers improved security over traditional key-based entry. However, it faces limitations including low-light image issues, Wi-Fi instability, and the processing constraints of the ESP32-CAM.
To improve performance, the project recommends using more powerful hardware like Raspberry Pi, adding lightweight machine-learning models, securing communication with encryption, and using infrared imaging. Overall, the system demonstrates the potential of affordable AI-powered security solutions for smart homes and secure facilities.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.