<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Pattern &#x2F; shape recognition software]]></title><description><![CDATA[<p dir="auto">Hello all,</p>
<div>is there a pattern or shape recognition software that is Isadora compatible? There is the famous "Face osc" that detects human face and send various parameters in osc format to izzy in localhost or in a network</div>
<div>[https://vimeo.com/26098366](https://vimeo.com/26098366)</div>
<div>But what I'd like is to be able to track other things (for example across, like a christian cross). is it possible with waht software?</div>
<div>Thanks</div>]]></description><link>https://community.troikatronix.com/topic/897/pattern-shape-recognition-software</link><generator>RSS for Node</generator><lastBuildDate>Wed, 10 Jun 2026 09:10:30 GMT</lastBuildDate><atom:link href="https://community.troikatronix.com/topic/897.rss" rel="self" type="application/rss+xml"/><pubDate>Mon, 07 Oct 2013 06:21:48 GMT</pubDate><ttl>60</ttl><item><title><![CDATA[Reply to Pattern &#x2F; shape recognition software on Mon, 07 Oct 2013 23:46:53 GMT]]></title><description><![CDATA[<p dir="auto">I looked into this about a year ago and never found this.. annoying! But hey-ho I've found it now :)</p>
]]></description><link>https://community.troikatronix.com/post/8696</link><guid isPermaLink="true">https://community.troikatronix.com/post/8696</guid><dc:creator><![CDATA[Skulpture]]></dc:creator><pubDate>Mon, 07 Oct 2013 23:46:53 GMT</pubDate></item><item><title><![CDATA[Reply to Pattern &#x2F; shape recognition software on Mon, 07 Oct 2013 23:41:35 GMT]]></title><description><![CDATA[<div style="text-align:left">No it is a few years old already. Early augmented reality library. It is getting toward the end of its life as AR is pretty much completely focused on mobile devices these days.</div>]]></description><link>https://community.troikatronix.com/post/8695</link><guid isPermaLink="true">https://community.troikatronix.com/post/8695</guid><dc:creator><![CDATA[Fred]]></dc:creator><pubDate>Mon, 07 Oct 2013 23:41:35 GMT</pubDate></item><item><title><![CDATA[Reply to Pattern &#x2F; shape recognition software on Mon, 07 Oct 2013 23:38:46 GMT]]></title><description><![CDATA[<p dir="auto">Nice find <a class="plugin-mentions-user plugin-mentions-a" href="https://community.troikatronix.com/uid/8">@Fred</a> - when did this come out? Is it a new thing?</p>
]]></description><link>https://community.troikatronix.com/post/8694</link><guid isPermaLink="true">https://community.troikatronix.com/post/8694</guid><dc:creator><![CDATA[Skulpture]]></dc:creator><pubDate>Mon, 07 Oct 2013 23:38:46 GMT</pubDate></item><item><title><![CDATA[Reply to Pattern &#x2F; shape recognition software on Mon, 07 Oct 2013 23:36:14 GMT]]></title><description><![CDATA[<p dir="auto">ARToolkit will do what you want with a bit of work. You can train your own markers with not so much difficulty.Here is a how to <a href="https://vimeo.com/2361984" rel="nofollow ugc">https://vimeo.com/2361984</a>. I have made my own markers with the c++ version of this library but not the QC version. I dont know what features it has.</p>
<div style="font-family:Arial, Verdana;font-size:10pt;font-style:normal;font-variant:normal;font-weight:normal;line-height:normal">Here is a tutorial on training new markers</div>
<div>http://www.artoolworks.com/support/library/Creating_and_training_new_ARToolKit_markers</div>
<div>There are limitations (like the image needs a continuous border but you can be creative with this) on training new markers. In openCV you can make new arbitrary object definitions but it is not a plug and play solution.</div>
<div>Fred</div>]]></description><link>https://community.troikatronix.com/post/8693</link><guid isPermaLink="true">https://community.troikatronix.com/post/8693</guid><dc:creator><![CDATA[Fred]]></dc:creator><pubDate>Mon, 07 Oct 2013 23:36:14 GMT</pubDate></item><item><title><![CDATA[Reply to Pattern &#x2F; shape recognition software on Mon, 07 Oct 2013 21:43:45 GMT]]></title><description><![CDATA[<p dir="auto">I looked into this - a lot! There are things called fiducials or fiducial markers. These are used a lot with touch screens/touch screen surfaces:</p>
  
https://vimeo.com/33114239
  
But to be honest for what you want - no not really. if you do find anything then please let me know.
<p dir="auto">I did try and create a patch which took a screen grab of a live feed and compared it so when it matched up again within a 10% varience it sent a trigger.... It became very very complex though!</p>
<p dir="auto">On a side note. AR technology such as Layar and Aurasma can detect 2D images so it must be possible.</p>
]]></description><link>https://community.troikatronix.com/post/8691</link><guid isPermaLink="true">https://community.troikatronix.com/post/8691</guid><dc:creator><![CDATA[Skulpture]]></dc:creator><pubDate>Mon, 07 Oct 2013 21:43:45 GMT</pubDate></item></channel></rss>