Face Recognition With Raspberry Pi + OpenCV + Python

Summary

This video from Crow Electronics demonstrates how to use a Raspberry Pi and open source software to create a facial recognition system. It covers the setup with necessary hardware, installing packages, capturing facial images, training the model with Python scripts, and finally, using the trained model for real-time face identification. The tutorial also extends the project by integrating a servo motor controlled by the Raspberry Pi's GPIO pins, responding to recognized faces. The video highlights the ease of implementing machine learning with accessible tools and open source software.

Takeaways

• 🤖 The video is a tutorial on how to use a Raspberry Pi to recognize faces with the help of open source software.
• 📷 OpenCV and the Python face recognition package are the two main tools used for real-time computer vision and face detection.
• 🛠️ A Raspberry Pi, official camera module, micro SD card, power supply, HDMI cord, monitor, mouse, and keyboard are the hardware requirements.
• 💻 The Raspberry Pi 4 Model B is recommended for its extra computing power.
• 🔍 The camera module needs to be enabled in the Raspberry Pi configuration menu for the project to work.
• 📝 The 'headshots_pycam.py' Python script is used to take photos of faces for training the face recognition model.
• 👤 Users should take around 10 photos of their face from different angles for better recognition.
• 📁 A separate folder is created for each person's face photos to store the training images.
• 🔧 The 'train_model.py' script is used for training the model with the collected face images.
• 📡 The 'facial_rec.py' script runs the identification process, displaying a live stream and identifying known faces.
• 🔄 The Raspberry Pi can differentiate between known and unknown faces, labeling them accordingly.
• 🛠️ By modifying the 'facial_rec.py' script, the Raspberry Pi can control a servo or other mechanisms using GPIO pins when a known face is detected.
• 👍 The video credits OpenCV, the face recognition package, and Carolyn Dunn for their contributions to the software used in the project.

Q & A

What is the main purpose of the video?

The main purpose of the video is to demonstrate how to use a Raspberry Pi with open source software to recognize faces and control a servo based on face recognition.

Which open source software is mentioned for real-time computer vision problems?

OpenCV is mentioned as the open source software for solving real-time computer vision problems.

What is the role of the Python face recognition package?

The Python face recognition package computes bounding boxes around a face in real time, aiding in the face recognition process.

What are the hardware requirements for setting up the face recognition system with Raspberry Pi?

The hardware requirements include a Raspberry Pi, an official camera module, a micro SD card, a power supply, an HDMI cord and monitor, a mouse and keyboard, and optionally a servo for additional control.

Why is a Raspberry Pi 4 Model B recommended for this project?

The Raspberry Pi 4 Model B is recommended due to its extra computing power which is invaluable for running the machine learning algorithms required for face recognition.

How can one enable the camera interface on the Raspberry Pi?

The camera interface can be enabled through the Raspberry Pi configuration menu, found under the 'Preferences' and then the 'Interfaces' tab.

What is the purpose of the 'headshots_pycam.py' Python script?

The 'headshots_pycam.py' script is used to take photos of faces using the official Raspberry Pi camera for training the face recognition model.

How many photos of a face should be taken for the training process?

It is suggested to take around 10 photos of a face, including different angles, for better recognition accuracy during the training process.

What is the command to start the face recognition training process?

The command to start the training process is 'python train_model.py', run from the 'facial_recognition' directory.

How does the Raspberry Pi identify a known face and respond?

When a known face is identified, the Raspberry Pi draws a yellow box around the face and writes the person's name next to it in the live stream window.

What can be done to control a servo using face recognition results?

The Raspberry Pi can be programmed to send signals via the GPIO pins to control a servo, activating it when a known face is recognized and keeping it inactive for unknown faces or no face at all.

Outlines

00:00

🤖 Raspberry Pi Face Recognition Setup

This paragraph introduces a project where a Raspberry Pi is used to recognize faces using open source software. The narrator explains the synergy between open source software and Raspberry Pi, highlighting two key tools: OpenCV for real-time computer vision and the Python face recognition package. The project involves training the Raspberry Pi to identify a person's face and then using that recognition to control a servo. The required hardware is listed, including a Raspberry Pi 4 Model B for its computing power, an official camera module, a micro SD card, and other accessories. The process starts with setting up the Raspberry Pi, enabling the camera, and installing necessary packages. The user is guided to take photos of their face for training the model and to run a Python script for training the face recognition system.

05:00

🛠️ Enhancing Raspberry Pi with Face-Controlled Servo

The second paragraph delves into the practical application of the face recognition system by integrating it with a servo. The narrator demonstrates how to modify the Python code to send signals via the Raspberry Pi's GPIO pins when a known face is detected. This allows the servo to rotate, creating an interactive element to the project. The video shows a practical example where the servo only activates when the narrator's face is recognized, otherwise, it remains inactive. The narrator expresses gratitude to the developers of OpenCV and the face recognition package, as well as to Carolyn Dunn for creating software that integrates these systems effectively. The paragraph concludes by emphasizing the potential of this software for various projects and ends with a sign-off until the next video.

Keywords

💡Raspberry Pi

Raspberry Pi is a series of small, single-board computers developed to promote the teaching of basic computer science in schools and in developing countries. In the video, it is the central device used for building a facial recognition system, showcasing its versatility and computational capabilities.

💡Open Source Software

Open source software refers to a type of software whose source code is available to the public for use, modification, and enhancement. In the context of the video, open source software like OpenCV and the Python face recognition package are utilized to create a real-time face recognition system on the Raspberry Pi.

💡OpenCV

OpenCV, which stands for Open Source Computer Vision Library, is a library of programming functions mainly aimed at real-time computer vision. In the video, OpenCV is highlighted as a crucial tool for solving real-time computer vision problems, such as detecting and processing faces in images or video streams.

💡Python Face Recognition Package

The Python face recognition package is a library used for facial recognition tasks. It is mentioned in the video as a tool that computes bounding boxes around faces in real time, which is essential for the Raspberry Pi to recognize and identify individuals.

💡Machine Learning

Machine learning is a subset of artificial intelligence that provides systems the ability to learn and improve from experience without being explicitly programmed. In the video, the Raspberry Pi uses machine learning algorithms to train and recognize human faces, demonstrating the accessibility of this technology.

💡Microprocessor

A microprocessor is a small computer processor that integrates the functions of a computer's central processing unit (CPU) on a single integrated circuit. In the video, the Raspberry Pi's microprocessor is highlighted for its role in processing the facial recognition tasks, emphasizing the computational power needed for such applications.

💡Camera Module

The camera module mentioned in the script refers to the official Raspberry Pi camera module, which is used to capture images or video. In the context of the video, it is essential for capturing the facial images required for training the face recognition system.

💡Training Model

In machine learning, a training model refers to the process of teaching an algorithm to make predictions or decisions based on input data. In the video, the script describes how the Raspberry Pi is trained to recognize individual faces using a set of images, which is a fundamental step in the facial recognition process.

💡GPIO Pins

GPIO stands for General Purpose Input/Output and refers to a group of pins on a Raspberry Pi that can be used to control or read signals from external devices. In the video, the script explains how GPIO pins can be used to send signals to control a servo motor when a known face is recognized.

💡Servo

A servo is a type of motor that includes a closed-loop system for precise control of position or speed. In the video, the Raspberry Pi is programmed to activate a servo motor when it recognizes the user's face, demonstrating a practical application of the facial recognition system.

Highlights

Using Raspberry Pi and open source software like OpenCV and the Python face recognition package to create a facial recognition system.

Raspberry Pi's open source nature makes it an excellent platform for real-time computer vision and machine learning projects.

The tutorial demonstrates how to train the Raspberry Pi to recognize a specific face using the official camera module.

The face recognition system uses bounding boxes to detect and identify faces in real-time.

List of required components for setting up the facial recognition system, including the Raspberry Pi 4 and official camera module.

Instructions on enabling the camera interface in the Raspberry Pi configuration menu.

Using the 'headshots_pycam.py' script to take photos of faces for training the model.

Creating a folder with the user's name to store the captured face images for training.

Running the 'train_model.py' script to analyze the dataset and train the model to recognize faces.

The trained model can identify known faces and write the person's name next to the detected face in real-time.

Demonstration of the live face recognition system using the Raspberry Pi camera and the trained model.

The system can differentiate between known and unknown faces, labeling them accordingly.

Exploring the potential of using the Raspberry Pi's GPIO pins to control external devices like servos based on face recognition.

Adding code to the 'facial_rec.py' script to activate a servo when a known face is detected.

The servo moves when the Raspberry Pi recognizes the user's face, demonstrating the practical application of the system.

The tutorial credits the open source communities behind OpenCV and the face recognition package for their contributions to the project.

A call to action for viewers to explore the potential of the software for their own projects, highlighting the limitless applications.

Transcripts

hey gang team here at crow electronics

and today we're making our raspberry pi

recognize who we are by our face

[Music]

open source software and raspberry pi's

go together hand in hand

the two excellent examples of this are

opencv which provides a huge

free resource to solve real-time

computer vision problems

and the python face recognition package

which computes

bounding boxes around a face in real

time

these are the two systems that we will

use to make this all come together

machine learning has never been more

accessible i will show you exactly how

to have your raspberry pi microprocessor

be able to spot human faces

how to train it to know your face and to

run code

so that it will successfully identify

you when it sees you

then i'll take it another step and show

you how you can use your face to control

the servo which is attached to

the raspberry pi

before me on the table is everything you

need to get this system

up and running really fast starting off

you're going to want a raspberry pi

official camera

module version 2. you can also use the

raspberry pi high quality camera

a micro sd card a official raspberry pi

power supply

a hdmi cord and monitor to connect to a

mouse and keyboard

and for this i'm using a raspberry pi 4

model b as the extra computing power

oomph that the raspberry pi provides is

invaluable

you're also going to want some way to

connect the micro sd card

to your computer so you can flash it

so we're going to get started with all

the packages installed already

to follow along at this point go to the

article to get the steps to install the

packages on your setup

once you power up the raspberry pi

you're going to see this familiar

background booted up

now first let's open up the raspberry pi

configuration menu

found by using the top left menu

scrolling over preferences

and make sure that the camera found

under the interfaces tab

is enabled if you had to enable this

setting go ahead and reset the raspberry

pi so that the changes can take

effect now open up the file explorer

which is the folder button on the top

left of the screen

jump into the folder located in the home

pi directory

facial recognition and then look for the

python code called headshots

underscore pycam.py this python code

will let us take some photos

of our faces using the official

raspberry pi camera right click

and open up that python script with

either funny or genie

both are just python language

interpreter softwares and alter the line

of code here

with your name in my case timmy

then save this script next go back into

the folder structure and open up

the photos folder here you're going to

add another folder with your name

this folder is then going to be the

location where the photo files will end

up then jump back into the python editor

where we had

saved that python code and run it this

will open up a little window and a

terminal window

which you can use to save images of your

face press the spacebar key to take an

image

take around 10 and then the q key to

close the window once you've done so

provide a couple of different angles of

your face so it can determine your

dimensions

better once you close the software

you're going to be able to see the

images of your face

stored in the folder you created for

your name you can add other faces using

this same method too

with all that sorted we can get into the

machine learning step

the pictures we took will now be used by

the python code train

underscore model dot py any pictures in

the dataset folder location will be

analyzed by this code when we run this

program

so open up a new terminal using the

black console button on the top left

and type the following pressing enter

after each line cd

space facial underscore recognition this

will get us into the right folder

and then python space train underscore

model dot py

which is going to run our desired code

this will start the training process

which you can see occurring for each

image

that i took of my face

then with that completed the raspberry

pi 4 model b will have learned what your

face looks like

so let's give it a go to run the

identification code that will identify

faces and when it finds a train face

will write their name next to it

start by opening up a new terminal just

the same as before

then type the following and press enter

after each step

cd facial underscore recognition and

then

python facial underscore req dot

py once you press enter it's going to

take around 5 seconds to boot up and run

then you're going to see a small window

pop up with a live stream of the

raspberry pi camera

aim the camera at your face and if it

puts a yellow box around your head

and names you correctly you have done it

the raspberry pi camera is now searching

live for faces

it will also determine if it's a known

or an unknown face if it's unknown it's

going to write

unknown next to it and if it's a face of

the name of the person that it knows

it's going to write that person's name

next to it

this example code is awesome and lets

you experiment to see

when the software can or cannot track

your face i find if you tip your head to

the side a couple of degrees it's going

to completely disable the facial

recognition and

if you cover your nose as well it

struggles close the terminal window or

press ctrl c

on the keyboard to stop it running

[Music]

so we can do many things with this now

simply to start we can now jump into the

folders with the python code and alter

just a couple of lines

in that code in the facial underscore

rec dot py

so that every time a known face is seen

it's going to send out signals via the

gpio pins of the raspberry pi

these general purpose input and output

pins can be used to control an almost

endless amount of sensors and mechanisms

so

for this i'm going to get a servo to

rotate when the raspberry pi system sees

my

face if it sees an unknown face or no

face at all

it's not going to activate this servo

all this

by adding just six lines of code to the

script

all the code i'll be adding here is

completely explained in the guide

controlling standard servers with

raspberry pi

linked down below so hopefully you can

see everything what i'm going to do is

hide my face from the camera by putting

my thumb just in front of it

the server you're going to be able to

see from the top and when i show up my

face

you're going to see the server move you

can see it's active

see down here

it's red because my skin is pink

and now i'm going to show my face

boom straight away as soon as it saw my

face

nice huge thanks go to the opencv

and facial recognition package teams

that work on the amazing machine

learning software

that we have running on this raspberry

pi both

are really good open source software

also a huge thank you goes to carolyn

dunn

who created the majority of the amazing

software which makes these two systems

work together

so well there's just so much potential

with this software to take projects to

amazing places

so that's it for today until next time

stay cozy