Transformation (PCA)

Several transformation methods are available in the EnMAP-Box. You can find them in the Processing Toolbox under EnMAP-Box ‣ Transformation. The usual way to apply these methods is to use a Fit … algorithm first and then apply it to an image with Transform Raster.

This recipe demonstrates the basic workflow of applying transformations using a principle component analysis (Fit PCA) and the test dataset.

See also

You can find all the available transformation algorithms here.

  1. Open the test dataset

  2. In the processing toolbox go to EnMAP-Box ‣ Transformers ‣ Fit PCA

    • Specify enmap_berlin.bsq under Raster
    • Under Output Transformer specify an output file path and click Run
  3. Now open EnMAP-Box ‣ Transformers ‣ Transform Raster

    • Select enmap_berlin.bsq as input Raster
    • Under Transformer click and select the output .pkl file from the Fit PCA algorithm
    • Specify an output filepath for the transformed raster under Transformation and click Run
    ../../_images/example_pca.png

    Results of a PCA transformation: input image on the upper left, RGB representation of the first 3 components on the upper right and singleband gray visualisation of the same components on the bottom.