Wrong prediction 2 different face (Score 0.56)

ageitgey / face_recognition

The world's simplest facial recognition api for Python and the command line

MIT License

52.81k stars 13.43k forks source link

Wrong prediction 2 different face (Score 0.56) #779

Open blinkbink opened 5 years ago

blinkbink commented 5 years ago

face_recognition version: 1.2.3
Python version: 3.6
Operating System: Ubuntu 18.04

Description

I'm running with cuda, tryng to compare similarity with selfie face and face on National Identity Card then got score 0.56 (under 0.60) on different people. How i can handle this ? any advices ?

i try set score 0.55 but many prediction (same people score like 0.57 or 0.58)

olgeorge commented 5 years ago

IMHO, I would start by checking the alignment on the faces, if it's not perfect you may want to try a different face detector

blinkbink commented 5 years ago

IMHO, I would start by checking the alignment on the faces, if it's not perfect you may want to try a different face detector

Ah ok, i would to try thank you

manishm123 commented 5 years ago

first align in RGB. Then use num_jitters value up till 5 while generating encoding. Then keep the threshold below 0.45 to avoid false positives.