1
<!-- meta page description: wxGUI Supervised Classification Tool -->
2
<!-- meta page index: topic_gui|GUI -->
6
<b>Supervised Classification Tool</b> (wxIClass) is
7
a <em><a href="wxGUI.html">wxGUI</a></em> compoment which allows the
8
user to create training areas and generate spectral signatures. The
9
resulting signature file can be used as input for
10
<em><a href="i.maxlik.html">i.maxlik</a></em>
11
or as a seed signature file for
12
<em><a href="i.cluster.html">i.cluster</a></em>.
13
<em>WxIClass</em> can be launched from the Layer Manager
14
menu <i>Imagery → Classify image → Interactive input for
15
supervised classification</i> or via command line
16
as <em>g.gui.iclass</em>.
19
<em>wxIClass</em> currently allows you to:
22
<li>create training areas
23
(using customized <em><a href="wxGUI.vdigit.html">vector
24
digitizer</a></em>)</li>
25
<li>show histograms for each band and class (category)</li>
26
<li>show coincidence plots for each band</li>
27
<li>show raster cells that match training areas
28
(within the number of standard deviations specified)</li>
29
<li>specify color of class</li>
30
<li>write signature file</li>
31
<li>import vector map</li>
32
<li>export vector map with attribute table</li>
38
<img src="iclass_frame.jpg" border="1" alt="Supervised Classification Tool">
43
<em>wxIClass</em> performs the first pass in the GRASS two-pass supervised image
44
classification process; the GRASS module
45
<em><a href="i.maxlik.html">i.maxlik</a></em> executes the second pass.
46
Both programs must be run to generate a classified map in GRASS
50
<em>wxIClass</em> is an interactive program that allows the user to create
51
multiple training areas for multiple classes and calculate the spectral
52
signatures based on the cells that are within the training areas.
53
During this process the user will be
54
shown histograms for each image band.
55
The user can also display the cells of the image bands which fall within
56
a user-specified number of standard deviations from the means in the spectral signature.
57
By doing this, the user can see how much of the image
58
is likely to be put into the class associated with the signature.
61
The spectral signatures are composed of region means and covariance matrices.
62
These region means and covariance matrices are used in
63
the second pass (<em><a href="i.maxlik.html">i.maxlik</a></em>)
64
to classify the image.
67
Alternatively, the spectral signatures generated by <em>wxIClass</em> can be
68
used for seed means for the clusters in
69
<em><a href="i.cluster.html">i.cluster</a></em>.
74
<a href="wxGUI.html">wxGUI</a><br>
75
<a href="wxGUI.components.html">wxGUI components</a>,
76
<a href="wxGUI.iscatt.html">Interactive Scatter Plot Tool</a>
81
user <a href="http://grasswiki.osgeo.org/wiki/WxIClass">wiki</a> page
82
and <a href="http://trac.osgeo.org/grass/wiki/wxGUIDevelopment/wxIClass">development</a> page.
87
<a href="http://www.cvut.cz">Czech Technical University in Prague</a>, Czech Republic<br>
90
<a href="http://www.cvut.cz">Czech Technical University in Prague</a>, Czech Republic
93
<i>$Date: 2014-04-20 19:57:39 +0200 (Sun, 20 Apr 2014) $</i>