<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<p>Hoi Gilles,</p>
<p>thx for the update <br>
</p>
<p>Just checked OpenFace in detail and it says it uses dlib (or
openCV) as well, so you have something in common :).</p>
<p>In case some is curious about the difference of the both, is well
explained here
<a class="moz-txt-link-freetext" href="https://www.quora.com/What-is-the-difference-between-dlib-and-opencv">https://www.quora.com/What-is-the-difference-between-dlib-and-opencv</a><br>
</p>
<div class="moz-cite-prefix">On 23.08.2018 15:41, Gilles Caulier
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:CAHFG6sEY+HAsK9np7bMFr3LB-JVEPtZhd__y0C2Y=E8DaxkuUQ@mail.gmail.com">
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
<div dir="ltr">
<div>open face is Python library.<br>
</div>
<div>DK is C++/ Qt. it's not homogeneous.</div>
<div><br>
</div>
<div>We use Dlib neural network directly compatible with C/C++.</div>
<div><br>
</div>
<div><a href="http://dlib.net/ml.html" moz-do-not-send="true">http://dlib.net/ml.html</a><br>
</div>
<div><br>
</div>
<div>Gilles Caulier</div>
<div class="gmail_extra"><br>
<div class="gmail_quote">2018-08-23 15:36 GMT+02:00 Stefan
Müller <span dir="ltr"><<a
href="mailto:stefan.mueller.83@gmail.com"
target="_blank" moz-do-not-send="true">stefan.mueller.83@gmail.com</a>></span>:<br>
<blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px #ccc solid;padding-left:1ex">
<div text="#000000" bgcolor="#FFFFFF">
<p>Can I ask what kind of AI engine it is.</p>
<p>I cannot find any reference to OpenFace in the
digikam documentation, why not using this one?</p>
<p>regards</p>
<span class="HOEnZb"><font color="#888888">
<p>Stefan<br>
</p>
</font></span>
<div>
<div class="h5">
<div class="m_5402556905077404778moz-cite-prefix">On
23.08.2018 10:49, Gilles Caulier wrote:<br>
</div>
<blockquote type="cite">
<div dir="ltr">The Face Management improvements
using AI engine (deep learning) is integrate in
digiKam core, but the code need finalization and
improvements again. It cannot be yet used in
production.
<div><br>
</div>
<div>Gilles Caulier</div>
</div>
<div class="gmail_extra"><br>
<div class="gmail_quote">2018-08-23 10:26
GMT+02:00 NeiNei <span dir="ltr"><<a
href="mailto:neinei@gmx.net"
target="_blank" moz-do-not-send="true">neinei@gmx.net</a>></span>:<br>
<blockquote class="gmail_quote"
style="margin:0 0 0 .8ex;border-left:1px
#ccc solid;padding-left:1ex">Dear Gilles and
team,<br>
<br>
I just read about the DK 6 beta and
remembered then GSOC 2017 Project 4 digiKam
Face Management improvements. I wonder
whether the results of this project are
already integrated in digikam. Perhaps I
overlooked it in DK 5.x or DK 6 release
notes, so please forgive me to ask the same
thing again.<span
class="m_5402556905077404778HOEnZb"><font
color="#888888"><br>
<br>
-- NeiNei<br>
</font></span></blockquote>
</div>
<br>
</div>
</blockquote>
</div>
</div>
</div>
</blockquote>
</div>
<br>
</div>
</div>
</blockquote>
</body>
</html>