How face recognition works in deep learning?

We have access to a trained model through dlib that we can use. It does exactly what we need it to do — outputs a bunch of numbers (face encodings) when we pass in the image of someone’s face ; comparing face encodings of faces from different images will tell us if someone’s face matches with anyone we have images of.

Read more

How fast can we recognize a face?

Here, we find that recognizing faces takes around 190 ms in addition. What happens during this additional time? Three main hypotheses can be formulated. First, the ability to rapidly recognize familiar faces could rely on the same feed-forward mechanisms that have been posited for superordinate categorization.

Read more