https://bugs.kde.org/show_bug.cgi?id=518026

--- Comment #5 from Ondrej Zizka <[email protected]> ---
Note, the parameters I used are quite "strict" so that I have minimum false
positives. The goal was to cluster good-quality face regions (well lit, sharp,
large enough). 
Still, the model has issues with people with hats/caps, large sunglasses,
and/or smooth faces, and puts them quite close together.

-- 
You are receiving this mail because:
You are watching all bug changes.

Reply via email to