|
@@ -4,6 +4,11 @@
|
|
|
user-specified raster map layer. The module calculates textural features
|
|
|
based on spatial dependence matrices at 0, 45, 90, and 135
|
|
|
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>
|
|
|
<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
|
|
@@ -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
|
|
|
(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>
|
|
|
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>
|
|
|
</ul>
|
|
|
-
|
|
|
-<h2>NOTES</h2>
|
|
|
|
|
|
+<p>
|
|
|
+The computational region should be set to the input map with
|
|
|
+<b>g.region rast=<input map></b>, or aligned to the input map
|
|
|
+with <b>g.region align=<input map></b> if only a subregion
|
|
|
+should be analyzed.
|
|
|
+
|
|
|
+<p>
|
|
|
Importantly, the input raster map cannot have more than 255 categories.
|
|
|
|
|
|
<h2>EXAMPLE</h2>
|