<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<p>Gilles <br>
</p>
<p>thanks a lot for this clarification. <br>
</p>
<p>IA in DK ! I look forward to see more on this! if he can do all
this for us , but I beleive that's the purpose :-)</p>
<p>did you look also to my second point:</p>
<p>also a problem I have (not new in DK6), after a search, when I'm
looking <br>
to the unconfirmed, I see different proposals, and when the
proposal is <br>
incorrect, if I enter the correct name, then it seems to become
the <br>
standart proposal for most of the remaining unconfirmed.<br>
<br>
is there something I'm doing wrong ?</p>
I have also another error: the tag "unconfirmed" is no more visible
(I have removed it) , but not able to re-create it as it still
exist. How to make it visible again?<br>
regards<br>
Frederic<br>
<br>
<div class="moz-cite-prefix">Le 12/11/2018 à 07:37, Gilles Caulier a
écrit :<br>
</div>
<blockquote type="cite"
cite="mid:CAHFG6sGSCxt=dQV6gv_q4yt2ySwxqKKjvR2j1JQR7TaY3fpgGQ@mail.gmail.com">
<meta http-equiv="content-type" content="text/html; charset=utf-8">
<div dir="ltr">
<div dir="ltr">
<div dir="ltr">
<div dir="ltr"><br>
<br>
<div class="gmail_quote">
<div dir="ltr">Le dim. 11 nov. 2018 à 11:22, frederic
chaume <<a href="mailto:frederic.chaume@gmail.com"
moz-do-not-send="true">frederic.chaume@gmail.com</a>>
a écrit :<br>
</div>
<blockquote class="gmail_quote" style="margin:0px 0px
0px 0.8ex;border-left:1px solid
rgb(204,204,204);padding-left:1ex">Hi all<br>
<br>
trying to experiment the face recognition from DK6B2,
and I see now <br>
there are 4 different algorithms. What are the
differences ?<br>
<br>
</blockquote>
<div><br>
</div>
<div>This is 4 different algorithms to process face
fingerprints while faces recognition.</div>
<div><br>
</div>
<div>This is not the face detection processing, which is
another one.</div>
<div><br>
</div>
<div>Detection is one step, recognition is another one. </div>
<div>The 3 first one recognition algorithm are standard
method more and less efficient to process recognition
:</div>
<div><br>
</div>
<div>LPB : the original method and the first one
implemented in DK.</div>
<div><br>
</div>
<div><a
href="https://en.wikipedia.org/wiki/Local_binary_patterns"
moz-do-not-send="true">https://en.wikipedia.org/wiki/Local_binary_patterns</a><br>
</div>
<div><br>
</div>
<div>EigenFace : This algorithm was never finalized in
DK when FR have been implemented in DK. It's not
finalized and given for testing and compare with LPB</div>
<div><br>
</div>
<div><a href="https://en.wikipedia.org/wiki/Eigenface"
moz-do-not-send="true">https://en.wikipedia.org/wiki/Eigenface</a><br>
</div>
<div><br>
</div>
<div>FisherFace : This algorithm is an improvement of
EigenFace. It's not fully implemented and given to
compare with LPB (it do not store data in database has
i remember).</div>
<div><br>
</div>
<div><a
href="http://note.sonots.com/SciSoftware/FaceRecognition.html"
moz-do-not-send="true">http://note.sonots.com/SciSoftware/FaceRecognition.html</a><br>
</div>
<div><br>
</div>
<div>LPB, EighenFace, and Fisherface use OpenCV library
implementation as well. So the performance are
relevant of OpenCV code. In DK, we have a template
implementation of recognition engine which can be
extended through virtual methods, as plenty of
algorithm variant exists to perform face recognition. </div>
<div><br>
</div>
<div>Between LPB, EigenFace and FisherFace, LPB is the
most faster. The recognition efficience is mostly the
same (good recognition vs false results). </div>
<div>Eigen and Fisher run more slowly than LPB.</div>
<div><br>
</div>
<div>These algorithms need at least 6 faces already
tagged by end users with the same person to recognize
to start to give suitable results, but if more
reference are given, it must be better. Typically you
provide samples to use to process future comparison
using face histogram stored in database. You can only
provide real face sample to compare. You cannot teach
about false positive results. The teach process still
basic.</div>
<div><br>
</div>
<div>The last one is more tedious and promising but it's
so far not optimized. It's an IA algorithm using deep
learning based on DLib. You teach face to the neural
network and it store data in database. The result are
good if you teach many faces to the IA. The result are
good, but the speed no. It's slow and require more end
user action to work. So this one need a lots of
improvement for the future and cannot be used as well
actually. This IA can teach for false positive
detected as flower seen as a face for ex. So the teach
process is more complete, but require more data
storage in database.</div>
<div><br>
</div>
<div>IA and deep learning are the future and look
promising. It's also a very interesting project to
implement (from a student viewpoint), as IA start to
be used everywhere in computer science. So i'm sure
that we will found new students to work on it later,
as it still a lots of work to do on it.</div>
<div><br>
</div>
<div>So the only one to use for the moment is LPB.</div>
<div><br>
</div>
<div>Best</div>
<div><br>
</div>
<div>Gilles Caulier</div>
<div><br>
</div>
<div> </div>
<blockquote class="gmail_quote" style="margin:0px 0px
0px 0.8ex;border-left:1px solid
rgb(204,204,204);padding-left:1ex">
also a problem I have (not new in DK6), after asearch,
when I'm looking <br>
to the unconfirmed, I see different proposals, and
when the proposal is <br>
incorrect, if I enter the correct name, then it seems
to become the <br>
standart proposal for most of the remaining
unconfirmed.<br>
<br>
is there something I'm doing wrong ?<br>
<br>
<br>
thanks for your help<br>
<br>
<br>
regards<br>
<br>
frederic<br>
<br>
</blockquote>
</div>
</div>
</div>
</div>
</div>
</blockquote>
<br>
</body>
</html>