8. Signature threshold


threshold_tool Signature threshold

This tab allows for the definition of a classification threshold for each spectral signature. All the signatures contained in the Training input are listed. Thresholds defined in this tool are applied to classification only if Threshold value in Algorithm is 0.

This is useful for improving the classification results, especially when spectral signatures are similar. Thresholds of signatures are saved in the Training input.

If threshold is 0 then no threshold is applied and all the image pixels are classified. Depending on the selected Algorithm the threshold value is evaluated differently:

  • for Minimum Distance, pixels are unclassified if distance is greater than threshold value;
  • for Maximum Likelihood, pixels are unclassified if probability is less than threshold value (max 100);
  • for Spectral Angle Mapping, pixels are unclassified if spectral angle distance is greater than threshold value (max 90).

8.1. Signature threshold

  • input_table Signature threshold: table containing the following fields;
    • MC ID: signature Macroclass ID;
    • MC Name: signature Macroclass Name;
    • C ID: signature Class ID;
    • C Name: signature Class Name;
    • MD Threshold: Minimum Distance threshold; this value can be edited;
    • ML Threshold: Maximum Likelihood threshold; this value can be edited;
    • SAM Threshold: Spectral Angle Mapping threshold; this value can be edited;
  • reset: reset all signatures thresholds to 0 (i.e. no threshold used);

8.2. Automatic thresholds

  • Set threshold input_number enter: set the defined value as threshold for all the highlighted signatures in the table;
  • Set threshold = σ * input_number enter: for all the highlighted signatures, set an automatic threshold calculated as the distance (or angle) between mean signature and (mean signature + (σ * v)), where σ is the standard deviation and v is the defined value; currently works for Minimum Distance and Spectral Angle Mapping;