Skip to content

What IS face clustering? #1162

Closed Answered by marcelklehr
31337-4554551n asked this question in Q&A
Discussion options

You must be logged in to vote

Hey @31337-4554551n
So, faces in photos first need to get recognized, so that the software knows there's a face in that picture, where in the picture it is, and what the face looks like (this is expressed as a vector). To aggregate similar faces in groups, the software searches for clusters in the vector space of face vectors. If some vectors are close enough together (simplifying here), then they will be put into the same cluster and appear as photos of one person in the user interface. If you add new photos and there's a face whose vector is close to an existing cluster's vectors, it will be put into the same cluster. This process of figuring out which group a face might belong to is ca…

Replies: 1 comment 3 replies

Comment options

You must be logged in to vote
3 replies
@31337-4554551n
Comment options

@marcelklehr
Comment options

@31337-4554551n
Comment options

Answer selected by 31337-4554551n
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants