Hi<div><br></div><div>Regarsding segmentation, has anyone implemented a method to segment an image in a unsupervised way? (i.smap is supervised).</div><div><br></div><div>Or anyone developed some method to do image segmentation?</div>
<div><br></div><div><br></div><div>Thanks</div><div>Nikos<br><br><div class="gmail_quote">On Mon, Jan 18, 2010 at 11:22 PM, Markus Neteler <span dir="ltr"><<a href="mailto:neteler@osgeo.org">neteler@osgeo.org</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;"><div class="im">On Mon, Jan 18, 2010 at 6:30 PM, Nikos Dumakis <<a href="mailto:nikosdu1980@gmail.com">nikosdu1980@gmail.com</a>> wrote:<br>
> Greetings all<br>
> I've been following GRASS-user discussion related with pos-classigfication,<br>
> classification, aggregation and so on. But, while I was readingh those<br>
> emails I figured that I will need to perform, before classification, an<br>
> image segmentation to derive objects.<br>
<br>
</div>You don't need to perform a segmentation before doing classification but<br>
i.smap is doing it in a combined way.<br>
<div class="im"><br>
> Can anyone give me a clue abvout that because in GRASS book, I only founded<br>
> Image segmentation related with processing large quantities of vectorial<br>
> data (DEM's).<br>
<br>
</div>(DEMs are raster data)<br>
<br>
What you need to do is to prepare the statistics with i.gensigset. See<br>
"radiometric & geometric supervised" in<br>
<br>
<a href="http://grass.osgeo.org/wiki/Image_classification" target="_blank">http://grass.osgeo.org/wiki/Image_classification</a><br>
<br>
(The book is explaining that as well)<br>
<br>
Hope this helps,<br>
<font color="#888888">Markus<br>
</font></blockquote></div><br></div>