Maximum likelihood classification assumes that the statistics for each class in each band are normally distributed and calculates the probability that a given pixel belongs to a specific class. Unless you select a probability threshold, all pixels are classified. Each pixel is assigned to the class that has the highest probability (that is, the maximum likelihood). If the highest probability is smaller than a threshold you specify, the pixel remains unclassified.

ENVI implements maximum likelihood classification by calculating the following discriminant functions for each pixel in the image (Richards, 1999):

Where:

i = class

x = n-dimensional data (where n is the number of bands)

pi) = probability that class ωi occurs in the image and is assumed the same for all classes

i| = determinant of the covariance matrix of the data in class ωi

Σi-1 = its inverse matrix

mi = mean vector

Reference: Richards, J. Remote Sensing Digital Image Analysis, Berlin: Springer-Verlag (1999), 240 pp.

Follow these steps:

  1. From the Toolbox, select Classification > Supervised Classification > Maximum Likelihood Classification. The Maximum Likelihood Classification dialog appears.
  2. Select an Input Raster and perform optional spatial and spectral subsetting, and/or masking.
  3. Select the Input ROIs that represent the classes. Statistics from the ROIs are used as input to the Maximum Likelihood calculation.
  4. Optional: In the Threshold Probability field, enter a scalar value for all classes or array of values, one per class, from 0 to and 1. For arrays, the number of elements must equal the number of classes. Pixels with a value lower than the threshold will not be classified. The default value is 0.00000000. The threshold is a probability minimum for inclusion in a class. For example, a value of 0.9 will include fewer pixels in a class than a value of 0.5 because a 90 percent probability requirement is more strict than allowing a pixel in a class based on a chance of 50 percent.
  5. Optional: Specify a filename and location for the Output Rule Raster. A rule raster is a greyscale image that shows intermediate classification results, where each band represents a rule raster for each class. With Maximum Likelihood classification, pixel values contain a maximum likelihood discriminant function with a modified Chi Squared probability distribution. Higher rule image values indicate higher probabilities.
  6. Specify a filename and location for the Output Raster (the classification raster).
  7. Enable the Display result check box to display the output rule raster and/or output rule raster in the Image window when processing is complete. Otherwise, if the check box is disabled, the raster can be loaded from the Data Manager.
  8. Enable the Preview check box to see a preview of the settings before you click OK to process the data. The preview is calculated only on the area in the Image window. See Preview for details on the results. To preview a different area in your image, pan and zoom to the area of interest and reenable the Preview option.
  9. To run the process on a local or remote ENVI Server, click the down arrow and select Run Task in the Background or Run Task on remote ENVI Server name. The ENVI Server Job Console will show the progress of the job and will provide a link to display the result when processing is complete. See the ENVI Servers topic for more information.

  10. Optional: Click Open in Modeler to see a model-based version of this tool that shows how the tool is constructed from individual tasks.
  11. Click OK. ENVI adds the resulting output to the Data Manager and, if the Display Result check box was enabled, adds the layer to the Layer Manager and displays the output in the Image window.