Authentication through face recognition + image anti spoofing check - using WebRTC and Haar waterfall classifiers (POC)

phase 1: assigning user identifier + collecting images that can classify the identified person

phase 2: network training by feeding the AI with the images of the right person identified / classified

phase 3: recognition of the person

-face detection/recognition is done using Haar waterfall classifiers.

-image spoofing detection is done by asking the user to smile at random time intervals

https://docs.opencv.org/3.3.0/d7/d8b/tutorial_py_face_detection.html

http://www.willberger.org/cascade-haar-explained/

https://www.bogotobogo.com/python/OpenCV_Python/python_opencv3_Image_Object_Detection_Face_Detection_Haar_Cascade_Classifiers.php

https://towardsdatascience.com/face-recognition-how-lbph-works-90ec258c3d6b