Supervised Classification Techniques

Abstract

Supervised classification is the procedure most often used for quantitative analysis of remote sensing image data. It rests upon using suitable algorithms to label the pixels in an image as representing particular ground cover types, or classes. A variety of algorithms is available for this, ranging from those based upon probability distribution models for the classes of interest (such as outlined in Chap. 3) to those in which the multispectral space is partitioned into class-specific regions using optimally located surfaces. Irrespective of the particular method chosen, the essential practical steps are:

• 1. Decide the set of ground cover types into which the image is to be segmented. These are the information classes and could, for example, be water, urban regions, croplands, rangelands, etc.

• 2. Choose representative or prototype pixels from each of the desired set of classes. These pixels are said to form training data. Training sets for each class can be established using site visits, maps, air photographs or even photointerpretation of a colour composite product formed from the image data (either in hardcopy form or on the colour display of an image analysis system). Often the training pixels for a given class will lie in a common region enclosed in a border. That region is then often called a training field.

• 3. Use the training data to estimate the parameters of the particular classifier algorithm to be used; these parameters will be the properties of the probability model used or will be equations that define partitions in the multispectral space. The set of parameters for a given class is sometimes called the signature of that class.

• 4. Using the trained classifier, label or classify every pixel in the image into one of the desired ground cover types (information classes). Here the whole image segment of interest is typically classified. Whereas training in Step 2 may have required the user to identify perhaps 1 % of the image pixels by other means, the computer will label the rest by classification.

• 5. Produce tabular summaries or thematic (class) maps which summarise the results of the classification.