diaLab7UnsupervisedClassification110222

diaLab7UnsupervisedClassification110222 - Geo 4037c Digital...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon
Geo 4037c Digital Image Analysis Unsupervised Classification
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
INTRODUCTION In this lab you will be performing an unsupervised classification in ERDAS IMAGINE. IMAGINE software uses the ISODATA algorithm discussed in lecture. An unsupervised classification is the simplest way to classify spectral signatures – Signatures are automatically created by the algorithm. – Useful first step in the classification process – Can help you get to know your image so that you can set the spectral signatures when performing supervised classifications in the next weeks.
Background image of page 2
INTRODUCTION You will submit your evaluated ISODATA image Your subsetted and rectified satellite image And the DOQQ you are using to help classify land use.
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Step 1. Open ERDAS IMAGINE, and set your Session Preferences. Step 2. Click on the DataPrep icon. The Data Preparation window opens.
Background image of page 4
Step 3. In the Data Preparation menu click on Unsupervised Classification. The Unsupervised Classification window opens.
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Step 4 . In the Unsupervised Classification window under the Input Raster File dialog box, click the Folder Button and find and enter your subsetted image filename from your previous Subsetting Lab. Make sure you have selected the correct folder. Step 5 . Under Output File dialog box, click the Folder Button to navigate to the folder where you want the isodata image saved and enter isodata_lastname.img as the name
Background image of page 6
Step 6. Set Initial Cluster Options: Enter the following information: Under Clustering Options : Number of Classes: 12 Under Processing Options
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 8
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 03/30/2011 for the course GISC 4037C taught by Professor Roberts during the Spring '10 term at FAU.

Page1 / 31

diaLab7UnsupervisedClassification110222 - Geo 4037c Digital...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online