1. From the Toolbox, select Spectral > n-Dimensional Visualizer > n-Dimensional Visualizer New Data.
  2. To restore a saved state, select Spectral > n-Dimensional Visualizer > n-Dimensional Visualizer Saved Data (see Managing n-D Visualizer States).

    The n-D Visualizer Input File dialog appears.

  3. Select the file to extract the n-D scatter plots from (typically an MNF file).
  4. If the input file is an MNF result, spectrally subset the MNF data to exclude noise bands determined by reviewing the eigenimages and eigenvalue plot.

  5. Click OK.
  6. For speed and clarity, an ROI is used to limit the number of pixels that are input into the n-D Visualizer. You should compute the ROI as a threshold from the PPI results. If only one ROI is present for the input image, it is automatically used as input to the n-D Visualizer. If more than one ROI is present, the n-D Visualizer Input ROI dialog appears. Select the ROI to use.

Note: If the ROI imported into the n-D Visualizer was defined using the PPI, then the data cloud shows only the corners of the data cloud. Normally, mixed pixels occupy the center of the data cloud, but mixed pixels are not included in an ROI defined using the PPI:

A status box appears while the ROI is loaded. The n-D Visualizer and n-D Controls dialogs appear.