Closed teolemon closed 6 years ago
Hey, I'm Rahil from India. I'd like to work on this issue.
My name is Akshat and I am from India. I would like to clarify and establish the issue, here. We require to detect faces using any face detection algorithm but then to filter out only those faces that are known to the machine learning model from training phase (rejecting those that are also printed on packaging).
So finally 1) detect the face (I'd like to use dlib and it's more accurate than voila jones and other algorithms) 2) filter out and detect only those images that are required and already known Am I Correct?
Many cloud computer vision have face detection algos, but they might find a face on packaging while we're looking for faces of users. Allow to whitelist "known faces" and to flag actual faces.