Skip to content

Tagima/IoT_AccessControl

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 

Repository files navigation

IoT Access Control

Project for access control through edge computing

In this project, I used a Convolutional Neural Network (CNN) to make a face recognition application. It runs on a Raspberry Pi and the faces are detect through Haar Cascade Classifiers. Since this system is meant to be used in remote areas, the communication system used LoRa.

This work is the Final Project for Control and Automation Engineering Bachelor Degree at Federal University of Itajubá (UNIFEI).


Hardware requisites:

Dependencies:

This project was made on Ubuntu 16.04 LTS using a laptop Intel Core i5 8GB RAM and no GPU. Considering you're using a Linux, you'll need:

  • Python 3.5
  • OpenCV python
  • Pytorch

This section needs to be improved by letting all commands needed to install all dependencies.

On Raspberry Pi, I used the Raspbian Buster Full. You'll need:

  • Python 3.7
  • OpenCV python
  • Pytorch

To save some time, I'll let the image I used available here very soon :)

Contents:

Host

Host has all the code I used to gather the training set data and generate the CNN.

Raspberry

Raspberry has all the code that'll run on the edge device, which is the facial detection & recognition and LoRa communication.

About

Project for access control through edge computing

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors