<div dir="ltr"><div>I wasn't aware of that bug. I did validate it did that in the past, and the bug you pasted seems to agree, but I haven't specifically validated that lately (since that bug was patched) and the pictures that were once updated with that tag still have it obviously. It seems that the fix implemented in that bug would cause ignored faces to behave the way you would expect. I assume that since they are saved in the digikam database, as long as you keep the same database they will not be re-detected by future detection runs even if run against the same picture. I wonder how someone in my situation can easily remove the ignored tag from the 1300 pictures I have that have that tag stored in the metadata? I hate to delete them in digikam as I don't want them to be removed from the digikam database and then have to re-ignore them. Maybe exiftool would be the easiest method?</div><div><br></div><div>Separately on the question of "matching" ignored faces. I currently have 41 faces that have been "recognized" as matches to existing faces that I have not confirmed in my ignored group in digikam (some as recent as Nov of last year). It seems to me that once you mark a face as ignored, digikam does match future faces against that group. I can only imagine that the trained model for the ignored face is a mess because there are many different faces inside that one group.<br></div><div><br></div><div><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Thu, Mar 2, 2023 at 12:34 PM Marc Palaus <<a href="mailto:marcpalaus@hotmail.com">marcpalaus@hotmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<div>
<blockquote>
<p>Adding blurry face regions to the "ignored" tag will cause
other things to match those later. I've seen real people that
appear in multiple photos get "matched/recognized" against a
name of "ignored" because they were ignored in previous runs.</p>
</blockquote>
<p>Are you sure about that? I have never been suggested any face to
the "Ignored" group (and I have tagged thousands of pictures). In
the past, when you clicked on ignore, that "Ignored" would be
saved in the metadata, but it was fixed last September
(<a href="https://bugs.kde.org/show_bug.cgi?id=459537" target="_blank">https://bugs.kde.org/show_bug.cgi?id=459537</a>). I'd recommend you
delete that Ignored face region from the pictures they currently
have it, so those faces don't appear in other programs like
Pigallery2. In theory, the ignored tag shouldn't be used for the
face training (can a developer confirm that?).</p>
<p>As I said, I never had this issue. Clicking the red cross will
just remove that face from digikam (although if the picture is
scanned again, it will be re-detected), and the Ignore just hides
them into their own category, but without writing anything to the
pictures either.</p><br></div>
</blockquote></div></div>