In this exercise you will
learn advanced classification using the image processing capabilities of Idrisi
Andes. Start Idrisi and click Help and then
“IDRISI Tutorial”. Scroll down to Tutorial Part 5. The
data for this lab can be found in I:\Students\Instructors\Geoffrey_Duh\IDRISI\Advanced
IP. Please copy the files to your working folder on the local computer.
Complete exercises 5-1 through 5-5, which include the
following topics:
1) Bayes' Theorem and Maximum Likelihood Classification
2) Soft Classifiers I: Bayclass
Soft Classifier
3) Hardeners (forcing decision of class
membership)
4) Soft Classifiers II: Dempster-Shafer
Soft Classifier and BELCLASS
5) Dempster-Shafer and Classification Uncertainty
Read/skim the help section called Classification of Remotely Sensed Imagery
(pages 188-206) in “IDRISI Manual” before you begin. Skip the
sections on Hard Classifiers if you know what they are about. To quickly access
lab data, you can open the Idrisi Explorer,
click on the Projects tab, and set the working folder to your working space. This is done by right-clicking anywhere in the tab and selecting
“Change Object Folder.” Once you set the project folder, you need
to create a new project in your project folder. Right-click
on the tab and select “New Project.” Give the new project a
name before you continue. If you haven’t used Idrisi
before, getting familiar with IDRISI’s GUI
probably will be the most time-consuming part of this lab. Be patient! Be
explorative to learn the hidden functions of the GUI (e.g., double-click the
objects on the map)! Learn how other people picked the training sites! See what
information is in a .sig file!
Write a report that describes
the different results of the different classification techniques. Be sure
to include a map of each resulting classification as well as any tabular
results that will illustrate their differences.