Using Python Face Recognition library. It was built using dlib's state-of-the-art face recognition built with deep learning.
Clone this repository:
git clone https://github.com/endormi/face-recognition.git
Install requirements:
pip install -r requirements.txt
Test to see if it's installed correctly:
face_recognition ./img/known ./img/unknown
If you want to see the face distance calculated for each match in order to adjust the tolerance setting, you can use --show-distance true
face_recognition --show-distance true ./img/known ./img/unknown
If you simply want to know the names of the people in each photograph but don't care about file names
face_recognition ./img/known ./img/unknown | cut -d ',' -f2
-
groupfaces - Find the locations of the faces & how many people are in this image.
-
match - Match the face.
-
id - Identify images and draw a label with a name below the face.
To try other stuff, check the documentation