<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
<p>Hi,</p>
<p>now, some mor data....<br>
</p>
<p>After several runs and tagging face recogintion does not
recognize any more out of already found faces (~25k images, ~6k
faces not recognized ~14k already tagged). But there are <i>very
much faces very similar</i> to already recoginzed/tagged ones.</p>
<p>Is there a way for me to icrease recognition rate? <br>
</p>
<p>I've done some "case studies" with my data. Current settings
yolo_v3, with accuracy rate at<br>
</p>
<ul>
<li>100% does not suggest any recogniton</li>
<li>95% finds one downscaled/compressed jpg (rate to 10%
size=225kB, no edits)</li>
<li>90% one more suggestion but very inaccurate/wronn</li>
<li>85% found 3 more suggestions, one a perfect match, one a
fairly reasonable, one bad</li>
<li>80% aims to recoginze/suggest some more, but with a very low
recoginition rate (17/6000), and low match rate (10/71)<br>
</li>
</ul>
<p>As i mentioned, having lots of very similar faces assinged
already, i would assume this a poor recognition rate. (6k pics,
~20% very similar to already tagged ones, but not found any
suggestion.)<br>
</p>
<p>From the manual, it is suggested to remove tagged "weird" faces
(carneval or other not very clear representations), to prevent
false suggestions. But this would lead to a processing and
suggestion next run again, probably false again, wouldn't it?</p>
<p>Cheers, Gerhard<br>
</p>
</body>
</html>