Simple Facial Recognition project with Raspberry Pi
Vložit
- čas přidán 22. 03. 2023
- This is a very short & simple project/tutorial about Facial Recognition with just a Raspberry Pi and camera.
The commands for installing dependencies & cloning GitHub repo (in the right order)
sudo apt install cmake build-essential pkg-config git
sudo apt install libjpeg-dev libtiff-dev libjasper-dev libpng-dev libwebp-dev libopenexr-dev
sudo apt install libavcodec-dev libavformat-dev libswscale-dev libv4l-dev libxvidcore-dev libx264-dev libdc1394-22-dev libgstreamer-plugins-base1.0-dev libgstreamer1.0-dev
sudo apt install libgtk-3-dev libqtgui4 libqtwebkit4 libqt4-test python3-pyqt5
sudo apt install libatlas-base-dev liblapacke-dev gfortran
sudo apt install libhdf5-dev libhdf5-103
sudo apt install python3-dev python3-pip python3-numpy
git clone github.com/opencv/opencv.git
git clone github.com/opencv/opencv_cont...
mkdir ~/opencv/build
cd ~/opencv/build
cmake -D CMAKE_BUILD_TYPE=RELEASE \
-D CMAKE_INSTALL_PREFIX=/usr/local \
-D OPENCV_EXTRA_MODULES_PATH=~/opencv_contrib/modules \
-D ENABLE_NEON=ON \
-D ENABLE_VFPV3=ON \
-D BUILD_TESTS=OFF \
-D INSTALL_PYTHON_EXAMPLES=OFF \
-D OPENCV_ENABLE_NONFREE=ON \
-D CMAKE_SHARED_LINKER_FLAGS=-latomic \
-D BUILD_EXAMPLES=OFF ..
make -j$(nproc)
sudo make install
sudo ldconfig
Note that there is no penalty for typing the wrong command, just retype the right command and press "Enter" if that happens.
This cannot be done without the article from PiMyLifeUp:
pimylifeup.com/raspberry-pi-o...
Not sponsored but I thought would be helpful:
Here are my gears
Canon EOS M200 & 15-45mm EM F Lense: shorturl.at/lDLVX
Favorite Portable Light: shorturl.at/lmzW3
Studio Light: shorturl.at/hnsC0
Blue Yeti X Mic: shorturl.at/fpGJX
Great editing man! ill have to try this out for a vid eventually. Nice Kang Statue
Thanks for this. But the issue now is that the new pi camera module V3 only works with picamera2 library. Which doesn't seem to include the PiRGBarray
thanks for the video, i still have a question though, how do you clone the facial recognition thing from github in the first place after inputting all the commands you have put in the description? i am a bit lost on that please help me out
My code needs to use the values from the pickle file so cd myfolder must be used before it can run. Is there a way to write a script run? Please.
Thank you uploading. Could you please get the Raspberry Pi hardware, OS version, Python version, opencv version ? Does 64-bit OS work for you ?
Which algorithm you have used for face recognization
Hi, I've installed opencv, but getting errors during cmake.
Which part gives you the "face-recognition" folder that you show in the video?
Thanks
isnt this the same codes with core electronics?
Give code for the project
Bro can I do this for a final year project. I need the repos please
is there any way to improve the fps?
Hi! Would it be possible have the Raspberry Pi adjust the exposure so that the face is always properly exposed? If so, any idea how I can achieve this? Thank you!
That could be done with another ML algorithm or some light sensor
Thanks man, you didn't mentioned to clone the actual face_recognition folder?
That's a good point. Thanks man
which version of operating system are you using, Legacy bullseye or bookworm 64 or 32 bit, I'm trying for more than 1 week , and some of the packages are missing and cannot be installed . Thank you
he is using buster. I was using bookworm but switching to buster
hi, but where are those python codes you are using in this video? I installed both repo but nothing are there....and why we have to install 2 GitHub repo, i guess is a a bit confused
I used bullseye 64 bit. Bullseye 32 would work just less efficiently. Bookworm is a mystery to me.
I like your videos, keeping it simple, I am curious, Could this facial recognition be integrated to the next video's chatgpt chatbot so it can recognise who it is talking to.
It would be cool to have something that when you walk in the room it recognises you and asks how you are going, beginning the possibility of a conversation.
If it doesn't recognise you it could ask what your name is.
I may be getting way ahead of the basic abilities of connecting the two together. ???
Thanks for the good words! I think it can be hard to get to it, but not impossible. There are so many cool APIs and libraries now so you would be surprised how easy these things can be. I will definitely make a vid on this!
when i try to run sudo apt install libjpeg-dev libtiff-dev libjasper-dev libpng-dev libwebp-dev libopenexr-dev it shoes me E: Unable to locate package libjasper-dev
how do i fix that?
running on latest bullseyes(64 bit), everything updated
Same u found somethings ?
Can I used this method on Ubuntu os in Raspberry 4 ? I'm in lab now please reply..brother
Yes you can, there might be some libraries/dependencies missing but whenever a "missing dependency" error pops up, just Google how to install it, and continue with my tutorial.
Can I use Hp Webcam instead of a raspberry Pi camera? Please reply...
You certainly can, most USB camera should work
@@thomasthemaker how about my laptop camera?
I followed every step but I cant find the facial_recognition file please help
pip install face-recognition --no-cache-dir
What facial recognition system did you clone from github please?
I have the github repo clone and all necessary commands in the description section. Let me know if you have any other questions
@@thomasthemaker hi Thomas thank you for your speedy response, I have followed all the steps you have kindly described yet I have no face recognition repo, like yours is lated out, I'm not very good at this unfortunately
Sorry that is mean to say layed out
@@franklyproducer1 Hi, can you clarify further what do you mean not having face recog repo? At which step (command) did you encounter the error and can you paste the error in here?
@@thomasthemaker Thank you for the video, but you did not provide a link to the facial_recognition repo
I want to make a project on vehicle Anti theft system using raspberry Pi and face recognition
Will you help me
First time i am using raspberry Pi
Try looking into motionEye!
raspberry-valley.azurewebsites.net/MotionEye-OS/