<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"><html><head><meta content="text/html;charset=UTF-8" http-equiv="Content-Type"></head><body ><div style='font-size:10pt;font-family:Verdana,Arial,Helvetica,sans-serif;'>Hi, this is my first message to the list. I'm using Grass 6.4.3 under Linuxmint 16.<br><br><div><div class="post-text" itemprop="description"><p>I'm trying to make a supervised classification. <br></p> <p>After digitizing the training areas, I transformed them from vector to raster. Then I've done the following:</p><p><i><code>g.region rast=train_area_2013_03_05_raster@PERMANENT,2013_03_05_toar4@PERMANENT</code></i></p> <p>then</p> <p><i><code>i.group group=group subgroup=sub_group input=2013_03_05_toar4@PERMANENT,2013_03_05_toar5@PERMANENT,2013_03_05_toar3@PERMANENT</code></i></p> <p>and </p> <p><i><code>i.gensig trainingmap=train_area_2013_03_05_raster@PERMANENT group=group@PERMANENT subgroup=sub_group signaturefile=superv_class</code></i></p> <p>but the resulting signature file, only contains one character: "#".</p> <p>The output of <i>i.gensig</i> in the console is the following:</p> <pre><code><i>Finding training classes... 3 classes found Calculating class means... Calculating class covariance matrices... Signature 1 not invertible Signature 2 not invertible Signature 3 not invertible i.gensig complete.</i> </code></pre> <p>If I try: <i><code>i.maxlik group=group@PERMANENT subgroup=sub_group sigfile=superv_class class=results_class</code></i></p> <p>I obtain the following error message:</p> <p><i><code>ERROR: Unable to read signature file <superv_class></code></i> </p> <p>I've been searching, but I couldn't find the solution. </p> <p>I've tried this: http://gis.stackexchange.com/questions/11933/problem-running-i-gensigset-in-grass-any-ideas<a href="http://gis.stackexchange.com/questions/11933/problem-running-i-gensigset-in-grass-any-ideas"></a></p> <p>And read this: http://gis.stackexchange.com/questions/41418/i-maxlik-cannot-read-i-class-output-signature-file</p><p> But here, there's no solution suggested. As in this case, I also used <code>i.cluster</code> to generate an unsupervised signature file and <code>i.maxlik</code> reads this perfectly well.</p> <p>Here: http://lists.osgeo.org/pipermail/grass-user/2010-April/055821.html</p><p> there's another similar question, but the only answer says: "I suspect that either the training areas are suboptimal or are too small." What does suboptimal means? What is an optimal training area? How big should they be?</p><p>I have 30 areas, 10 for each class. They aren't too big because I have a small site to clasify.</p><p>What does <code>"<i>Signature X not invertible</i>"</code> means? Is this the real problem?</p> <p>Any idea? Thanks for your help!</p> </div></div><br>Lucas.<br></div></body></html>