Principal component analysis

From AWF-Wiki
(Difference between revisions)
Jump to: navigation, search
(Created page with "* In the search engine of the Processing Toolbox, type PCA and select '''DimensionalityReduction(pca)''' under Image Filtering of the Orfeo Toolbox. * Under the Parameter tab,...")
 
(Using OTB standalone)
 
(19 intermediate revisions by 2 users not shown)
Line 1: Line 1:
* In the search engine of the Processing Toolbox, type PCA and select '''DimensionalityReduction(pca)''' under Image Filtering of the Orfeo Toolbox.
+
= Using QGIS OTB plugin =
 +
* In the search engine of the Processing Toolbox, type {{typed|text=dimension}} and select '''DimensionalityReduction''' under Image Filtering of the Orfeo Toolbox.
 
* Under the Parameter tab, select Multispectral band file as the input layer.
 
* Under the Parameter tab, select Multispectral band file as the input layer.
 
* Select '''pca''' under the Algorithm tab.
 
* Select '''pca''' under the Algorithm tab.
 
* Enter 4 as the number of components.
 
* Enter 4 as the number of components.
* Specify the directory to save the output file.
+
* Under Inverse Output Image [optional] untick Open output file after running algorithm (See Screenshot below).  
* Untick output file after running algorithm (inverse output image) option.
+
 
* Click on {{button|text=Run}} to execute the algorithm.
 
* Click on {{button|text=Run}} to execute the algorithm.
 +
[[File:qgis_otb_pca.png|400px]]
  
 +
= Using OTB standalone =
 +
* Type into the search box of the Windows taskbar: {{typed|text=mapla.bat}} or navigate to C:\opt\OTB-7.2.0-Win64\mapla.bat in your Windows explorer. Click on mapla.bat to open Monteverdi Application Launcher.
 +
* In the search engine of Mapla, type {{typed|text=Dimension}} under Image Filtering double click '''Dimensionality Reduction'''.
 +
* Specify a multispectral image as Input Image.
 +
* Specify directory and name for the Output image. Select the output data type {{button|text=float}} from the pull-down list.
 +
* Select '''PCA''' from the drop-down list as Algorithm.
 +
* Enter 4 as number of components.
 +
* Click on {{button|text=Execute}}.
  
[[Category: Working with Raster Data]]
+
[[File:pca_otb.png|500px]][[File:pca_result.png|400px]]
 +
 
 +
[[category:QGIS Tutorial]]

Latest revision as of 21:12, 29 November 2020

[edit] Using QGIS OTB plugin

  • In the search engine of the Processing Toolbox, type dimension and select DimensionalityReduction under Image Filtering of the Orfeo Toolbox.
  • Under the Parameter tab, select Multispectral band file as the input layer.
  • Select pca under the Algorithm tab.
  • Enter 4 as the number of components.
  • Under Inverse Output Image [optional] untick Open output file after running algorithm (See Screenshot below).
  • Click on Run to execute the algorithm.

Qgis otb pca.png

[edit] Using OTB standalone

  • Type into the search box of the Windows taskbar: mapla.bat or navigate to C:\opt\OTB-7.2.0-Win64\mapla.bat in your Windows explorer. Click on mapla.bat to open Monteverdi Application Launcher.
  • In the search engine of Mapla, type Dimension under Image Filtering double click Dimensionality Reduction.
  • Specify a multispectral image as Input Image.
  • Specify directory and name for the Output image. Select the output data type float from the pull-down list.
  • Select PCA from the drop-down list as Algorithm.
  • Enter 4 as number of components.
  • Click on Execute.

Pca otb.pngPca result.png

Personal tools
Namespaces

Variants
Actions
Navigation
Development
Toolbox
Print/export