<![CDATA[This research presents the design and evaluation of an automatic locker system employing Local Binary Pattern Histogram (LBPH)-based facial recognition for secure, keyless access control. The system integrates a Logitech C270 webcam, Arduino Uno microcontroller, relay module, and solenoid door lock, with processing performed via a laptop interface. Performance was assessed through two protocols: a single-user variability test under different facial accessories, achieving a 66.7% recognition rate, and a multi-user discrimination test, which yielded 50% accuracy across diverse facial profiles. Results indicate LBPH’s robustness against moderate occlusions but notable decline with heavy facial coverage such as helmets and masks. These findings highlight the critical role of facial visibility in biometric reliability and offer practical insights for implementing facial recognition systems in real-world security applications]]>
