Selaa lähdekoodia

r.texture: update manual

git-svn-id: https://svn.osgeo.org/grass/grass/trunk@69882 15284696-431f-4ddb-bdfa-cd5b030d7da7
Markus Metz 8 vuotta sitten
vanhempi
commit
49110b4ac4
1 muutettua tiedostoa jossa 13 lisäystä ja 5 poistoa
  1. 13 5
      raster/r.texture/r.texture.html

+ 13 - 5
raster/r.texture/r.texture.html

@@ -4,6 +4,11 @@
 user-specified raster map layer. The module calculates textural features 
 user-specified raster map layer. The module calculates textural features 
 based on spatial dependence matrices at 0, 45, 90, and 135 
 based on spatial dependence matrices at 0, 45, 90, and 135 
 degrees for a <em>distance</em> (default = 1).
 degrees for a <em>distance</em> (default = 1).
+
+<p>
+The output of <em>r.texture</em> can be used as additional input for 
+image classification or image segmentation (object recognition).
+
 <p>
 <p>
 <em>r.texture</em> assumes grey levels ranging from 0 to 255 as input. 
 <em>r.texture</em> assumes grey levels ranging from 0 to 255 as input. 
 The input is automatically rescaled to 0 to 255 if the input map range is outside
 The input is automatically rescaled to 0 to 255 if the input map range is outside
@@ -31,9 +36,7 @@ over all angles for each measure. Optionally, using flag <b>-s</b> the output
 consists of four images for each textural feature, one for every direction
 consists of four images for each textural feature, one for every direction
 (0, 45, 90, 135).
 (0, 45, 90, 135).
 
 
-<p>
-The user must carefully set the resolution (using <em>g.region</em>) before
-running this program, or the computer may run out of memory.
+<h2>NOTES</h2>
 
 
 <p>
 <p>
 A commonly used texture model is based on the so-called grey level co-occurrence
 A commonly used texture model is based on the so-called grey level co-occurrence
@@ -104,9 +107,14 @@ level co-occurrence matrices (GLCM; after Haralick 1979).
 
 
 <li> Maximal Correlation Coefficient (MCC)</li>
 <li> Maximal Correlation Coefficient (MCC)</li>
 </ul>
 </ul>
-   
-<h2>NOTES</h2>
 
 
+<p>
+The computational region should be set to the input map with 
+<b>g.region rast=&lt;input map&gt;</b>, or aligned to the input map 
+with <b>g.region align=&lt;input map&gt;</b> if only a subregion 
+should be analyzed.
+
+<p>
 Importantly, the input raster map cannot have more than 255 categories.
 Importantly, the input raster map cannot have more than 255 categories.
 
 
 <h2>EXAMPLE</h2>
 <h2>EXAMPLE</h2>