Statistics
| Revision:

gvsig-geoprocess / org.gvsig.geoprocess / trunk / org.gvsig.geoprocess / org.gvsig.geoprocess.app / org.gvsig.geoprocess.app.mainplugin / src / main / resources-plugin / help / en / es.unex.sextante.gridAnalysis.supervisedClassificationB / supervisedclassificationb.xml @ 537

History | View | Annotate | Download (2.08 KB)

1
<?xml version='1.0' encoding='ISO-8859-1' standalone='yes' ?>
2
        <help>
3
                <element name="DESCRIPTION" text="This algorithm performs supervised classification (see Supervised classification for more information) but does not require a polygon layer with training areas. Instead, spectral signatures have to be defined entering statistical values in a table.&#10;" description="Description" type="0">
4
                </element>
5
                <element name="ADDITIONAL_INFO" text="" description="Additional information" type="0">
6
                </element>
7
                <element name="EXTENSION_AUTHOR" text="" description="Algorithm created by" type="0">
8
                </element>
9
                <element name="HELP_AUTHOR" text="" description="Help file created by" type="0">
10
                </element>
11
                <element name="USER_NOTES" text="" description="User notes" type="0">
12
                </element>
13
                <element name="INPUT" text="The bands to use for classification" description="Bands" type="3">
14
                </element>
15
                <element name="TABLE" text="The table with the definition of the spectral signatures" description="Classes" type="3">
16
                </element>
17
                <element name="METHOD" text="The assignment of values in the cells outside of the training areas also depend on the criteria used. This algorithms incorporates three of them:  &#10;*Paralelepiped &#10;*Minimum distance &#10;*Maximum likelihood  &#10;The user should check which of the algorithms produces the best classification of the image (this depends on the training areas as well as the characteristics of the images itself).  In the paralelepiped algorithm, some cells might not be classified (they will be asigned the no data value) if their signature is not similar to any of those defined by the training areas. The other algorithms will always classify a pixel into a given class." description="Method" type="3">
18
                </element>
19
                <element name="OUTPUT_DESCRIPTION" text="" description="Description" type="2">
20
                </element>
21
                <element name="CLASSIFICATION" text="The resultign layer with values representing the class to which each pixel has been assigned." description="Classification" type="2">
22
                </element>
23
        </help>
24
<?xml version='1.0' encoding='ISO-8859-1' standalone='yes' ?>