Image Classification

This exercise is designed to introduce you to image classification. You will produce a thematic map from your registered Kowloon - Hong Kong Island image using supervised and unsupervised methods of classification. These methods involve clustering pixels in the image based on either statistics generated from user defined training classes (supervised method), or image statistics in general (unsupervised methods).

First you will create a supervised classification. The four main steps to create the classification in ENVI are listed below;

Define training classes,
Select the decision rule,
Generate class statistics (create a signature) and classify each pixel in the image according to the decision rule, and
Post classification procedures.

To begin, open ENVI and display a standard false colour composite of the registered Kowloon - Hong Kong Island Landsat TM image.