SPEAR Independent Components (IC) analysis is similar to Principal Component (PC) analysis in that an input dataset is transformed into a new dataset containing new bands comprised of a linear combination of the input bands. Unlike PC, which produces uncorrelated output bands, IC analysis transforms a set of mixed, random signals into components that are mutually independent. The benefit compared to PC is that IC can distinguish features of interest even when they occupy only a small portion of the pixels in the image.

The applications of IC in remote sensing include dimension reduction, extracting characteristics of the image, anomaly and target detection, feature separation, classification, endmember extraction, noise reduction, and mapping.

  1. From the Toolbox, select SPEAR > SPEAR Independent Component Analysis. The SPEAR Independent Component Analysis Wizard displays the File Selection panel.
  2. Click Select Input File, choose a file, then click OK. The input image should be a multispectral file in any format readable by ENVI.
  3. To optionally process only a portion of the scene, click Select Subset. A small Select Spatial Subset dialog appears.
  4. Click Spatial Subset. The standard Select Spatial Subset dialog appears.
  5. Apply an optional mask to the data by clicking SelectMask Band and selecting the desired mask image.
  6. By default, output files are saved to the same directory and use the same rootname as the input file, minus any extension. Output files are appended with a unique suffix. To change the directory and/or root filename, click Select Output Filename.
  7. Click Next. The Select Parameters dialog appears.
  8. The Number of Output ICs field defaults to the number of input bands. Fewer IC bands will speed up processing but may exclude minor features. It is recommended that you accept the default for multispectral imagery. For hyperspectral imagery, you can modify this number to speed up processing.
  9. If you did not apply masking at file input, enter the Sample X/Y Resize Factors in the appropriate fields to sub-sample the data when calculating the IC transform. Sub-sampling reduces the IC sample size to fit into memory and increases computational speed. This option is valid only on images with an x,y size greater than 64. A setting of 1 (the default) does not change the data. For example, on an image with an x,y size greater than 64, a resize factor of 0.5 will use every other pixel in the statistics calculations and the IC sample. Setting this value to a small number could lose features of interest, as those pixels may be discarded. The upper limit is 1.0. The lower value limits x,y size after downsampling to 64. Required processing memory and available memory are displayed on the Wizard screen.
  10. Optionally, click Show Advanced Parameters to define additional settings.
  11. Click Next. The Examine Results dialog appears.

    The original image in natural color and the IC results in grayscale are opened in the display and are dynamically linked for comparison.

  12. Cycle through the IC bands using the ICA Result drop-down list or the Show Prev and Show Next buttons. Entries appended with “Dark” and “Bright” highlight the darkest or brightest pixels in the chosen IC band. Use the Animate ICA Bands option to examine the results.
  13. Optionally, click on the dotted bar in the histogram window or enter values in the fields at the top of the histogram window to explore different stretching options. Use Auto-Flicker to examine your results.
  14. Click Next after examining your results. Processing is complete; click Finish to exit the Wizard.