Projects / Ideas / Face recognition door entry on Raspberry Pi

Face recognition door entry on Raspberry Pi

AdvancedSecurityIdeaReviewed
In short

How do you build a face recognition door entry on Raspberry Pi?

A Pi camera recognises enrolled faces with OpenCV and the face_recognition library, and opens a door lock only for them. You need Raspberry Pi 5, Raspberry Pi 27 W USB-C power supply, SanDisk microSD card 32 GB (A1, Class 10), Raspberry Pi Camera Module 3, Raspberry Pi 5 to Camera cable (22 to 15 pin), Relay Module 5V, Solenoid lock 12 V, Rectifier Diode 1N4007 and 12 V 2 A DC adapter.

Level
Advanced
Time
About 360 min
Parts
9
An idea, not a guided build yet. Goal, parts and steps; no wiring, code or tests. Copy it to My Garage to plan it.
Goal

Run face detection and recognition on a Pi and act on the match distance.

How to build it

  1. Install OpenCV and face_recognition in a virtual environment
  2. Take 10 photos of each person and save their encodings
  3. Detect faces in the live camera frame and compare encodings
  4. Open the lock when the distance is below 0.5
  5. Keep a manual key: face systems can be fooled by photos

Related projects

Common questions

What parts do I need for the face recognition door entry on Raspberry Pi?

Raspberry Pi 5, Raspberry Pi 27 W USB-C power supply, SanDisk microSD card 32 GB (A1, Class 10), Raspberry Pi Camera Module 3, Raspberry Pi 5 to Camera cable (22 to 15 pin), Relay Module 5V, Solenoid lock 12 V, Rectifier Diode 1N4007 and 12 V 2 A DC adapter.

How long does the face recognition door entry on Raspberry Pi take to build?

About 360 minutes for a advanced maker.