SUMMARY
If you make a mistake in the facial recognition workflow and add an incorrect face to a collection of 15000 people, it is not possible to find the wrongly tagged face. Subsequent results are polluted. It would be nice to have an outlier detection tool that shows faces that seem to deviate from the majority of the faces in a person tag.

STEPS TO REPRODUCE
1.  Tag face with wrong name
2.  Search for face using "sort by recently modified" or "sort by face type"
3. 

OBSERVED RESULT
Incorrect sorting, unable to find wrongly tagged face

EXPECTED RESULT
Correct sorting, outlier face(s) visible on top or bottom of people item list.

SOFTWARE/OS VERSIONS
Windows: 11
macOS: 
(available in the Info Center app, or by running `kinfo` in a terminal window)
Linux/KDE Plasma: 
KDE Plasma Version: 
KDE Frameworks Version: 
Qt Version: 

ADDITIONAL INFORMATION