Bug 392024 - Feature request: group similar faces in "Unknown" faces
Summary: Feature request: group similar faces in "Unknown" faces
Status: RESOLVED FIXED
Alias: None
Product: digikam
Classification: Applications
Component: Faces-Workflow (show other bugs)
Version: 5.9.0
Platform: Microsoft Windows Microsoft Windows
: NOR normal
Target Milestone: ---
Assignee: Digikam Developers
URL:
Keywords:
Depends on:
Blocks:
 
Reported: 2018-03-18 20:46 UTC by MarcP
Modified: 2020-09-12 05:26 UTC (History)
3 users (show)

See Also:
Latest Commit:
Version Fixed In: 7.2.0
Sentry Crash Report:


Attachments

Note You need to log in before you can comment on or make changes to this bug.
Description MarcP 2018-03-18 20:46:09 UTC
This is not a big deal, but could improve usability.

When detecting and recognizing faces, Digikam could group faces by similarity in the "Unknown" person when it's very certain that they belong to the same person, even if that person's name is not in the database yet. That way, only writing the name of one of them would face-tag the whole group. Just an idea, I am not sure if it's even possible with the current face recognition engine.
Comment 1 Simon 2018-03-18 20:52:55 UTC

*** This bug has been marked as a duplicate of bug 384396 ***
Comment 2 caulier.gilles 2019-12-23 15:01:34 UTC
7.0.0-beta1 is out with new Face Recognition algorithm based on Deep
Learning/Neural Network API from OpenCV

https://download.kde.org/unstable/digikam/

Please test and give us a feedback

Thanks in advance
Gilles Caulier
Comment 3 MarcP 2019-12-23 15:08:28 UTC
Testing at this very moment :)

One thing about face recognition, is that new users wouldn't know what to do to start recognizing new faces. Basically you first have to detect the faces (can be done from the right-click menu too), then manually tag at least 4 or 5 faces for each person, and then run the face recognition algorithm. Maybe a little message with these instructions could be displayed to the user the first time they opened the recognition panel? (Like the one you get for the similarity search).

I am also trying to see how it works with an existing face database. Since so far I had only tried it with controlled face datasets.
Comment 4 caulier.gilles 2020-09-12 05:26:53 UTC
Fixed with #384396