<html>
<head>
</head>
<body>
<p>Well, at least it's not just me. Let's hope there's a way to
reproduce the issue, and hopefully a remedy can be forthcoming, as
the face recognition, along with the map data, is one of the key
items I wanted out of DigiKam. I'm just starting with it, having
just gotten it working with an external MySQL/MariaDB with 8.7, so
I'm ready to go forward and make great use of it.</p>
<p> --Chad</p>
<p><br>
</p>
<div class="moz-cite-prefix">On 7/11/2025 11:31 AM, Charlie
Gorichanaz wrote:<br>
</div>
<blockquote type="cite" cite="mid:CAKpjONPxi+K9DN_7M60P-4G++uNDBM=kkyXt_bM31pjGvCvqsg@mail.gmail.com">
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
<div dir="ltr">
<div>Wow, I actually am seeing the same behavior currently. For
the record, Arch linux cache files tell me I upgraded to 8.6.0
June 5, and then to 8.7.0 June 30. I don't think I did any
face tagging work since June 30 until I tried yesterday.</div>
<div><br>
</div>
<div>I previously had around 300 items in my "Unconfirmed"
folder according to the number after that word in parentheses,
but none were showing up when I clicked on it. I ran a
"Recognize faces only" on a large chunk of my albums with the
quality slider bumped down from 7 to 6, hoping to catch a lot
more faces. The end result changed that tag to say
"Unconfirmed (0)". Then I ran a full "Scan all images" process
on a section of my library I had not processed yet. It then
told me it found 282 faces, and my unknown tag increased to
now say "Unknown (3262)", but I still have "Unconfirmed (0)".</div>
<div><br>
</div>
<div>So maybe something about this broke in 8.7.0?!</div>
<div><br>
</div>
<div>
<div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature">
<div dir="ltr">
<div>—</div>
<div>Charlie Gorichanaz</div>
</div>
</div>
</div>
<br>
</div>
<br>
<div class="gmail_quote gmail_quote_container">
<div dir="ltr" class="gmail_attr">On Fri, Jul 11, 2025 at
5:46 AM Chad Bersche <<a href="mailto:chad@bersche.com" moz-do-not-send="true" class="moz-txt-link-freetext">chad@bersche.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>
<p>Hi Charlie, et. al</p>
<p>I have an Unconfirmed tag, but it has zero images in it,
even after multiple "recognize faces" runs. </p>
<p>Once I did the initial scan all images, the Unknown tag
had ~6000 images in it. I classified probably ~800 of
those naming individuals correctly. I then re-ran the
process as you indicated using "Recognize faces only" on
all of my albums. I watched it as it zoomed thru images,
showing faces in the process of those in the image that
it'd previously detected. At the conclusion of the face
detection, which took several minutes, it came back
stating it scanned over 5,533 images and found ZERO
faces. Nothing moved from Unknown to Unconfirmed. This
is the same outcome every single time I've tried this.<br>
</p>
<p>So, what now? I've been tempted to try to re-create the
training data, but haven't done so yet. <br>
</p>
<p> -- Chad</p>
<p><br>
</p>
<div>On 7/10/2025 10:07 PM, Charlie Gorichanaz wrote:<br>
</div>
<blockquote type="cite">
<div dir="ltr">
<div>Chad,</div>
<div><br>
</div>
<div>Do you have a tag called "Unconfirmed" alongside
your "Unknown" tag? I believe that's where the
detected-and-potentially-matched faces should end up,
waiting for you to confirm or reject them.</div>
<div><br>
</div>
<div>The doc describes this under the Face recognition
section, "To start this process, go to the workflow
tab, select <strong>Recognize faces only</strong>,
and then click <strong>Scan Collection For Faces</strong>.
The process will tag similar <strong>detected</strong>
faces with the appropriate People tag from your tag
tree, and the corresponding thumbnail will disappear
from the <strong>Unknown</strong> tag selection. The
thumbnail will appear in the <strong>Unconfirmed</strong>
tag section and will be added to the suggested face
tag section."</div>
<br>
<div>
<div dir="ltr" class="gmail_signature">
<div dir="ltr">
<div>—</div>
<div>Charlie Gorichanaz</div>
</div>
</div>
</div>
<br>
</div>
<br>
<div class="gmail_quote">
<div dir="ltr" class="gmail_attr">On Thu, Jul 10, 2025
at 7:14 PM Chad A. Bersche <<a href="mailto:chad@bersche.com" target="_blank" moz-do-not-send="true" class="moz-txt-link-freetext">chad@bersche.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">I've
been baffled by this as well. I'm running on Windows
11, DigiKam <br>
8.7, and downloaded all the modules. I let it grind
thru a bunch of my <br>
libraries overnight. It resulted in about 6000 images
in the Unknown <br>
category. I spent a a couple hours assigning names to
people in that <br>
list (sometimes up to 200-300 images). I still have
5500 in the Unknown <br>
bucket after classifying several hundred.<br>
<br>
After doing that, I went to run the "Recognize faces
only" with <br>
Accuracy=7, Search in set to "All Albums" and Tags
unchecked. Then when <br>
I do the "Scan collection for faces" nothing changes,
and all the same <br>
Unknown images stay in the same Unknown bucket.<br>
<br>
What am I doing wrong? I had hoped that tagging a
good number of faces <br>
before doing the recognition would improve its
accuracy, but it seems to <br>
just want me to do all the assignment work, which I
kinda don't want to do.<br>
<br>
I'm using an external SQL database, with the database
running on Linux, <br>
because I do use the same image libraries across
Windows clients.<br>
<br>
Thanks for any help/suggestions!<br>
<br>
-- Chad<br>
<br>
On 7/8/2025 10:43 PM, Gilles Caulier wrote:<br>
> Hi,<br>
><br>
> You need to first detect faces on albums before
you recognize them.<br>
> After detecting, manually tag a few faces with
names, at least a few<br>
> ones are enough to teach the AI for an automated
recognition.<br>
><br>
> Finally, run a recognition process and look as AI
recognizes similar<br>
> faces already registered in the model but not yet
tagged in the<br>
> database.<br>
><br>
> The workflow is explained in the online doc :<br>
> <a href="https://link.bersche.com/click/20qyoQWWIOi2.29UmT_C0unWi.UJlc-QSwsLm/hoVYqVvO/3s/link.bersche.com/click/JrntK3g7lIuw.vrQMszT3ZBH1.tlPdogxGHMJ/IxL1-iQT/3s/docs.digikam.org/en/left_sidebar/people_view.html" rel="noreferrer" target="_blank" moz-do-not-send="true">https://docs.digikam.org/en/left_sidebar/people_view.html</a><br>
><br>
> Best<br>
><br>
> Gilles Caulier<br>
><br>
> Le mer. 9 juil. 2025 à 02:08, robert lindsay<br>
> <<a href="mailto:robert.lindsay@gmail.com" target="_blank" moz-do-not-send="true" class="moz-txt-link-freetext">robert.lindsay@gmail.com</a>>
a écrit :<br>
>> This is under intel mac os and I installed
the modules it asked for in installation. Under face
recognition their are boxes for rebuilding and
training data, but i can't find on to start face
recognition on albums<br>
</blockquote>
</div>
</blockquote>
<div><img alt="" src="https://link.bersche.com/open/JrntK3g7lIuw.vrQMszT3ZBH1.tlPdogxGHMJ/1.gif" moz-do-not-send="true"></div>
</div>
</blockquote>
</div>
</blockquote>
<div style="visibility:hidden;"><img alt="" src="https://link.bersche.com/open/20qyoQWWIOi2.29UmT_C0unWi.UJlc-QSwsLm/1.gif" /></div></body>
</html>