Microchip Technology Inc. Demonstration of a Smart Door Lock Using Facial Recognition

Swapna Gurumani, Senior Arm Applications Engineer at Microchip Technology Inc., demonstrates the company’s latest edge AI and vision technologies and products at the 2024 Embedded Vision Summit. Specifically, Gurumani demonstrates her company's SAMA7G54 MPU running facial recognition backed by TensorFlow Lite.

When a person whose face is already enrolled presses a button, the smart door lock is unlocked. For anyone else, access is denied. Here Gurumani shows, using a single-core ARM Cortex-A7, without any neural-co-processor and running embedded Linux, the ability to implement facial recognition, object recognition, etc. The benefits include low power consumption, minimal complexity and fast time-to-market.