This tutorial demonstrates how to perform Unsupervised Classification of a Landsat 8 Image using Erdas Imagine software.
Unsupervised classification is a classification method which examines a large number of unknown pixels and divides into a number of clusters based on natural groupings present in the image values. unlike supervised classification, unsupervised classification does not require analyst-specified training data. The user manually identifies each cluster with land cover classes.
آی-ویدئو