<?xml version="1.0" encoding="UTF-8"?>
	<rss version="2.0"
		xmlns:content="http://purl.org/rss/1.0/modules/content/"
		xmlns:wfw="http://wellformedweb.org/CommentAPI/"
		xmlns:dc="http://purl.org/dc/elements/1.1/"
		xmlns:atom="http://www.w3.org/2005/Atom"

			>

	<channel>
		<title>Cycling 74  &#187;  Topic: I know this has been asked a thousand times but&#8230;.</title>
		<atom:link href="http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/feed" rel="self" type="application/rss+xml" />
		<link>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/feed</link>
		<description></description>
		<pubDate>Wed, 19 Jun 2013 18:37:59 +0000</pubDate>
		<generator>http://bbpress.org/?v=2.2.4</generator>
		<language></language>

		
														
					
				<item>
					<guid>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-34556</guid>
					<title><![CDATA[I know this has been asked a thousand times but&#8230;.]]></title>
					<link>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-34556</link>
					<pubDate>Sun, 11 Nov 2007 12:28:28 +0000</pubDate>
					<dc:creator>Andy</dc:creator>

					<description>
						<![CDATA[
						<p>Hi guys,</p>
<p>An incredibly cheeky question but hey, if you don&#8217;t ask you don&#8217;t get and I&#8217;m running out of time on a project.</p>
<p>I know this has been discussed many times by various people but&#8230;. does anybody have a simple working shape recognition system made with cv.jit objects that they would be willing to let me take a look at or describe the processes for &#8211; or any good papers suitable for someone with max knowledge but not necessarily any C knowledge?  </p>
<p>I have looked at a lot of papers but I&#8217;m no closer to getting a working system in max. I have tried things like cv.jit.learn etc but I cannot seem to get it to demonstrate any consistency. I&#8217;m assuming there must be some levels of pre-processing that I must do before calculating the moments?</p>
<p>(Basically I want to recognise simple shapes drawn into an LCD &#8211; not find shapes in a complex image)</p>
<p>Cheers</p>
<p>Andy</p>
						]]>
					</description>

					
					
				</item>

			
				<item>
					<guid>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116849</guid>
					<title><![CDATA[Re: I know this has been asked a thousand times but&#8230;.]]></title>
					<link>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116849</link>
					<pubDate>Mon, 12 Nov 2007 00:07:03 +0000</pubDate>
					<dc:creator>Rob Ramirez</dc:creator>

					<description>
						<![CDATA[
						<p>i don&#8217;t think the question is cheeky, and i don&#8217;t think the answer is trivial.  shape recognition is a very complicated affair.</p>
<p>i&#8217;m not sure if you&#8217;re asking for some pattern recognition algorithms, or how to make your video input better for the cv objects.  if it&#8217;s the former, i don&#8217;t know how much advice you will get.  if it&#8217;s the latter, you should get plenty of advice by searching the forum.</p>
<p>you also might want to check out the reactable application.</p>
						]]>
					</description>

					
					
				</item>

			
				<item>
					<guid>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116850</guid>
					<title><![CDATA[Re: I know this has been asked a thousand times but&#8230;.]]></title>
					<link>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116850</link>
					<pubDate>Mon, 12 Nov 2007 00:19:09 +0000</pubDate>
					<dc:creator>Andy</dc:creator>

					<description>
						<![CDATA[
						<p>As it happens my project includes reactivision so I&#8217;m aware of the principles behind how that particular system works.</p>
<p>The system I want would be very different &#8211; I want to be able to draw a free hand square into an LCD and have my system be able to distinguish between a square and a triangle for example &#8211; not find shapes in an image.</p>
<p>More research has told me that perhaps what I need to research is more aligned to sketch recognition rather than image analysis and I have since found an interesting paper that I am looking into &#8211; In case anyone else is interested in this subject:</p>
<p><a href="http://rationale.csail.mit.edu/publications/Sezgin2001Sketchbased.pdf" rel="nofollow">http://rationale.csail.mit.edu/publications/Sezgin2001Sketchbased.pdf</a> </p>
<p>If I get something working I&#8217;ll post a patch up &#8211; I&#8217;m sure there are others out there trying to do the same sort of thing.</p>
<p>In the mean time if anyone has any experience in this area and wishes to share knowledge it would be greatly appreciated.</p>
<p>Cheers</p>
<p>Andy</p>
						]]>
					</description>

					
					
				</item>

			
				<item>
					<guid>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116851</guid>
					<title><![CDATA[Re: I know this has been asked a thousand times but&#8230;.]]></title>
					<link>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116851</link>
					<pubDate>Sat, 17 Nov 2007 12:40:48 +0000</pubDate>
					<dc:creator>nesa</dc:creator>

					<description>
						<![CDATA[
						<p>Hi,</p>
<p>You should checkout a FTM/mnm library, there&#8217;s an example that does  <br />
what you describe &#8211; simple gesture recognition. It should be  <br />
somewhere in the Extras/ftm/mnm something menu.</p>
<p>Cheers,<br />
nesa</p>
<p>> The system I want would be very different &#8211; I want to be able to  <br />
> draw a free hand square into an LCD and have my system be able to  <br />
> distinguish between a square and a triangle for example &#8211; not find  <br />
> shapes in an image.</p>
						]]>
					</description>

					
					
				</item>

			
				<item>
					<guid>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116852</guid>
					<title><![CDATA[Re: I know this has been asked a thousand times but&#8230;.]]></title>
					<link>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116852</link>
					<pubDate>Sat, 17 Nov 2007 17:58:51 +0000</pubDate>
					<dc:creator>lists@lowfrequency.or</dc:creator>

					<description>
						<![CDATA[
						<p>It&#8217;s in the examples folder of the unzipped FTM files (from inside  <br />
the disk image).<br />
I am not having much luck getting it to work properly, though.  It  <br />
looks really interesting, are there any more examples for this out  <br />
there?  It mentions using the Wii remote, for instance.</p>
<p>Best<br />
Evan</p>
<p>On Nov 17, 2007, at 12:40 PM, nesa wrote:</p>
<p>> Hi,<br />
><br />
> You should checkout a FTM/mnm library, there&#8217;s an example that does  <br />
> what you describe &#8211; simple gesture recognition. It should be  <br />
> somewhere in the Extras/ftm/mnm something menu.<br />
><br />
> Cheers,<br />
> nesa<br />
><br />
>> The system I want would be very different &#8211; I want to be able to  <br />
>> draw a free hand square into an LCD and have my system be able to  <br />
>> distinguish between a square and a triangle for example &#8211; not find  <br />
>> shapes in an image.<br />
></p>
						]]>
					</description>

					
					
				</item>

			
				<item>
					<guid>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116853</guid>
					<title><![CDATA[Re: I know this has been asked a thousand times but&#8230;.]]></title>
					<link>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116853</link>
					<pubDate>Sat, 17 Nov 2007 18:16:44 +0000</pubDate>
					<dc:creator>Andy</dc:creator>

					<description>
						<![CDATA[
						<p>This sounds really interesting but I&#8217;m not sure where to find the files? </p>
<p>Cheers</p>
<p>Andy</p>
						]]>
					</description>

					
					
				</item>

			
				<item>
					<guid>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116854</guid>
					<title><![CDATA[Re: I know this has been asked a thousand times but&#8230;.]]></title>
					<link>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116854</link>
					<pubDate>Sat, 17 Nov 2007 18:18:47 +0000</pubDate>
					<dc:creator>Andy</dc:creator>

					<description>
						<![CDATA[
						<p>Ah. Found it. Cheers. Will have a play.</p>
<p>Andy</p>
						]]>
					</description>

					
					
				</item>

			
				<item>
					<guid>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116855</guid>
					<title><![CDATA[Re: I know this has been asked a thousand times but&#8230;.]]></title>
					<link>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116855</link>
					<pubDate>Sat, 17 Nov 2007 22:37:32 +0000</pubDate>
					<dc:creator>nesa</dc:creator>

					<description>
						<![CDATA[
						<p>Well, I think that ftm 1.x example(ez-hmm-something) didn&#8217;t work for  <br />
me until I changed who knows what, but now I have 2.x installed, and  <br />
mnm.follower-example works out of the box(after reading p help  <br />
subpatch)&#8230;</p>
<p>There&#8217;s also FTM mailing list and a wiki page, I think thats where  <br />
Wii remote example is&#8230;</p>
<p>
On Nov 17, 2007, at 6:58 PM, evan.raskob [lists] wrote:</p>
<p>> It&#8217;s in the examples folder of the unzipped FTM files (from inside  <br />
> the disk image).<br />
> I am not having much luck getting it to work properly, though.  It  <br />
> looks really interesting, are there any more examples for this out  <br />
> there?  It mentions using the Wii remote, for instance.<br />
><br />
> Best<br />
> Evan<br />
><br />
><br />
><br />
> On Nov 17, 2007, at 12:40 PM, nesa wrote:<br />
><br />
>> Hi,<br />
>><br />
>> You should checkout a FTM/mnm library, there&#8217;s an example that  <br />
>> does what you describe &#8211; simple gesture recognition. It should be  <br />
>> somewhere in the Extras/ftm/mnm something menu.<br />
>><br />
>> Cheers,<br />
>> nesa<br />
>><br />
>>> The system I want would be very different &#8211; I want to be able to  <br />
>>> draw a free hand square into an LCD and have my system be able to  <br />
>>> distinguish between a square and a triangle for example &#8211; not  <br />
>>> find shapes in an image.<br />
>></p>
						]]>
					</description>

					
					
				</item>

			
				<item>
					<guid>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116856</guid>
					<title><![CDATA[Re: I know this has been asked a thousand times but&#8230;.]]></title>
					<link>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116856</link>
					<pubDate>Sun, 18 Nov 2007 18:27:21 +0000</pubDate>
					<dc:creator>lists@lowfrequency.or</dc:creator>

					<description>
						<![CDATA[
						<p>It does &#8220;work&#8221; but not very well.  I think I need those magic numbers.</p>
<p>I found a few patches with FTM wiiremote examples, but nothing using  <br />
gesture analysis.  Any FTM people out there on the jitter list?</p>
<p>
Cheers<br />
Evan</p>
<p>
On Nov 17, 2007, at 10:37 PM, nesa wrote:</p>
<p>> Well, I think that ftm 1.x example(ez-hmm-something) didn&#8217;t work  <br />
> for me until I changed who knows what, but now I have 2.x  <br />
> installed, and mnm.follower-example works out of the box(after  <br />
> reading p help subpatch)&#8230;<br />
><br />
> There&#8217;s also FTM mailing list and a wiki page, I think thats where  <br />
> Wii remote example is&#8230;<br />
><br />
><br />
> On Nov 17, 2007, at 6:58 PM, evan.raskob [lists] wrote:<br />
><br />
>> It&#8217;s in the examples folder of the unzipped FTM files (from inside  <br />
>> the disk image).<br />
>> I am not having much luck getting it to work properly, though.  It  <br />
>> looks really interesting, are there any more examples for this out  <br />
>> there?  It mentions using the Wii remote, for instance.<br />
>><br />
>> Best<br />
>> Evan<br />
>><br />
>><br />
>><br />
>> On Nov 17, 2007, at 12:40 PM, nesa wrote:<br />
>><br />
>>> Hi,<br />
>>><br />
>>> You should checkout a FTM/mnm library, there&#8217;s an example that  <br />
>>> does what you describe &#8211; simple gesture recognition. It should be  <br />
>>> somewhere in the Extras/ftm/mnm something menu.<br />
>>><br />
>>> Cheers,<br />
>>> nesa<br />
>>><br />
>>>> The system I want would be very different &#8211; I want to be able to  <br />
>>>> draw a free hand square into an LCD and have my system be able  <br />
>>>> to distinguish between a square and a triangle for example &#8211; not  <br />
>>>> find shapes in an image.<br />
>>><br />
></p>
						]]>
					</description>

					
					
				</item>

			
				<item>
					<guid>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116857</guid>
					<title><![CDATA[Re: I know this has been asked a thousand times but&#8230;.]]></title>
					<link>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116857</link>
					<pubDate>Sun, 18 Nov 2007 18:45:04 +0000</pubDate>
					<dc:creator>generalh</dc:creator>

					<description>
						<![CDATA[
						<p></p>
						]]>
					</description>

					
					
				</item>

			
				<item>
					<guid>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116858</guid>
					<title><![CDATA[Re: I know this has been asked a thousand times but&#8230;.]]></title>
					<link>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116858</link>
					<pubDate>Sun, 18 Nov 2007 21:04:21 +0000</pubDate>
					<dc:creator>lists@lowfrequency.or</dc:creator>

					<description>
						<![CDATA[
						<p></p>
						]]>
					</description>

					
					
				</item>

			
				<item>
					<guid>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116859</guid>
					<title><![CDATA[Re: I know this has been asked a thousand times but&#8230;.]]></title>
					<link>http://cycling74.com/forums/topic/i-know-this-has-been-asked-a-thousand-times-but/#post-116859</link>
					<pubDate>Mon, 19 Nov 2007 00:34:18 +0000</pubDate>
					<dc:creator>Andy</dc:creator>

					<description>
						<![CDATA[
						<p>It seems to work ok for me. It distinguishes quite well between simple shapes so long as they are drawn in the same direction as the model. Also, lots (20+) of models seem to cause &#8216;bad&#8217; slow down. Still&#8230;..seems pretty good. Not 100% perfect, but good none the less.</p>
						]]>
					</description>

					
					
				</item>

					
		
	</channel>
	</rss>

