Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Dealing with misidentified faces #229

Closed
Snake883 opened this issue Feb 6, 2020 · 3 comments
Closed

Dealing with misidentified faces #229

Snake883 opened this issue Feb 6, 2020 · 3 comments

Comments

@Snake883
Copy link

Snake883 commented Feb 6, 2020

Situation: Lots of photos are misidentified, which is expected, but want a method to handle them better by the user.

  1. Want to quickly mark identified faces as ignore/exclude.

  2. Want a feature to manually identify the face. For example, there are two different faces in the photo, Facerecogniztion identifies two faces, unfortunately FaceRrecognition thinks they are the same face (and the same face shows up twice in the UI).

The way camera UI deal with face detection is nice to have. I like that a box is created around the face.

Thanks.

@matiasdelellis
Copy link
Owner

Hi @snakyjake1

You must tune the values of Minimum confidence, and Sensitivity

MMm.. I use 0.99 of minimum confidence and 0.4 of sensitivity..

@matiasdelellis
Copy link
Owner

Want to quickly mark identified faces as ignore/exclude.
Want a feature to manually identify the face. For example, there are two different faces in the photo, Facerecogniztion identifies two faces, unfortunately FaceRrecognition thinks they are the same face (and the same face shows up twice in the UI).

This is discussed in other issues, try to look for references. 😉

The way camera UI deal with face detection is nice to have. I like that a box is created around the face.

This I do not understand what you expect, but if you expect that when you click on the person, highlight the face on the Viewer app this does not depend on us .. There is no api for it .. 😞

@stalker314314
Copy link
Collaborator

We discussed what you are asking long time ago, and we refer to this as "2nd layer", above "automation layer". More details can be found in #168, #134 and #157. Novelty that you mentioned here is second point, which is basically "labeling" step - pick a detected face and "choose" person. I think this is sound idea, but I also think these are all "layer 2" features, and maybe we can just mention this in #168 and close this?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants