A Raspberry Pi Project

——Intelligent Facial Recognition System

Abstract

This is a TensorFlow project of the facial recognization which using NCS (Neural Compute Stick) on Raspberry Pi 3B+ platform. The project also uses Django and Tencent Cloud that providing the web platform. The project would like to build a safety and intelligent facial recognition system in AI era.

Background

Facial recognition is a widely used biological technology. In the MIT Technology Review, the world's top ten breakthrough technology list, Alipay "brush facial payment" was selected. It nearly 120 million users have used facial recognition so far.

Compared with other biological technologies (fingerprint recognition, voice recognition), facial recognition has the following advantages: The methods requires some people's coordinated actions, while facial recognition does not need passive coordination, when recording the biological record of a person attempting to log in. Only the facial can be more intuitive and more convenient to verify the identity of the person. Because compared with traditional biological technology, facial recognition is more convenient and accurate , economic, extensible , and many other advantages, can be widely used in security verification, monitoring, control and other aspects.

Flowchart

System Architecture

Objectives

My Website

✅Fast facial recognition
✅Real-time detection, followed by security
✅View camera content via web page
✅Smart home monitor and control via web page
✅All platform access(smart phone, pad, PC web)

Project QR

Quickly Access

Method

Flowchart

Code

Demo

Mid-term Presentation

Final Presentation

Key Words

Facial recognition, Deep learning, Smart home, Django, Movidius NCS, Raspberry Pi, IOT, CNN