First check if Python is installed
python3 -v
If it isn't:
sudo add-apt-repository ppa:jonathonf/python-3.6
sudo apt-get update
sudo apt-get install python3.6Next, install OpenCV
sudo apt-get update
sudo apt-get upgrade
sudo apt-get install build-essential cmake
sudo apt-get install python-devel numpy
sudo apt-get install gcc gcc-c++
sudo apt-get install libpng-devel
sudo apt-get install libjpeg-turbo-devel
sudo apt-get install jasper-devel
sudo apt-get install openexr-devel
sudo apt-get install libtiff-devel
sudo apt-get install libwebp-devel
sudo apt-get install git
git clone https://github.com/opencv/opencv.git
mkdir build
cd build
cmake ../You should see the following output: Python 2:
-- Interpreter: /usr/bin/python2.7 (ver 2.7.6)
-- Libraries: /usr/lib/x86_64-linux-gnu/libpython2.7.so (ver 2.7.6)
-- numpy: /usr/lib/python2.7/dist-packages/numpy/core/include (ver 1.8.2)
-- packages path: lib/python2.7/dist-packagesPython 3:
-- Interpreter: /usr/bin/python3.4 (ver 3.4.3)
-- Libraries: /usr/lib/x86_64-linux-gnu/libpython3.4m.o (ver 3.4.3)
-- numpy: /usr/lib/python3/dist-packages/numpy/core/nclude (ver 1.8.2)
-- packages path: lib/python3.4/dist-packagesThen, start the build with the following commands:
make
sudo make installThis will take a while (usually ~30 minutes)
Once it is successful, run the following python script to verify the installation in python:
import cv2 as cv
print(cv.__version__)Next, install dlib:
sudo apt-get install libgtk-3-dev
sudo apt-get install libboost-all-dev
wget https://bootstrap.pypa.io/get-pip.py
sudo python get-pip.py
sudo pip3 install numpy
sudo pip3 install scipy
sudo pip3 install scikit-image
sudo pip3 install dlibNext install openface:
git clone https://github.com/TadasBaltrusaitis/OpenFace.git
cd OpenFace
mkdir build
cd build
cmake -D CMAKE_BUILD_TYPE=RELEASE CMAKE_CXX_FLAGS="-std=c++11" -D MAKE_EXE_LINKER_FLAGS="-std=c++11" ..
makeFinally, install pandas and Flask
sudo pip3 install Flask
sudo pip3 install pandasClone Recogniser
cd ~
git clone https://github.com/saurabhschheda/Recogniser.git
cd RecogniserTo run:
python3 app.py --host=0.0.0.0
On a browser, navigate to the public IP address of the host on port 5000.
For example, if the host is on 192.168.0.2, navigate to 192.168.0.2:5000/upload