Face_recognition: how to measure confidence in this lib

Created on 23 Oct 2018  路  6Comments  路  Source: ageitgey/face_recognition

  • face_recognition version:
  • Python version:
  • Operating System:

Description

Describe what you were trying to get done.
Tell us what happened, what went wrong, and what you expected to happen.
IMPORTANT: If your issue is related to a specific picture, include it so others can reproduce the issue.

What I Did

Paste the command(s) you ran and the output.
If there was a crash, please include the traceback here.

Most helpful comment

I think he/she wants to know if its possible, along with returning true/false, can we also get some parameter which can tell how much confident the algorithm is that the answer is correct..like score out of 100 (%age) etc.

All 6 comments

Can you ask a more detailed question? Confidence of which part exactly?

I think he/she wants to know if its possible, along with returning true/false, can we also get some parameter which can tell how much confident the algorithm is that the answer is correct..like score out of 100 (%age) etc.

For getting confidence score, you can use classifiers like svm instead of the knn in face recognition module.

@sysgsoft are you saying that knn does not support returning confidence levels ?

@sysgsoft are you saying that knn does not support returning confidence levels ?

KNN is non parametric approach. It will not perform well if we have lot of data. while testing it will take more time. I think parametric approaches like SVM will perform better.

Thanks @sysgsoft
Can this library be used for SVM ? And if so, mind sharing how?

I saw this one issue asking for SVM but it has no reply yet
https://github.com/ageitgey/face_recognition/issues/477

Was this page helpful?
0 / 5 - 0 ratings

Related issues

Sparviero-Sughero picture Sparviero-Sughero  路  4Comments

lfjd05 picture lfjd05  路  3Comments

ramineniraviteja picture ramineniraviteja  路  5Comments

dav-ell picture dav-ell  路  3Comments

carlhung picture carlhung  路  6Comments