Unsupervised Classification using ERDAS Imagine

Classification is one of the very basic and important parts of Goespatial Technologies. Any satellite image will generally have 256 discrete values. Hence talking from layman’s point of view, every image will have around 256 classes. This implies that vegetation might be covered in 50 classes based on their DNs (As different type and stages of vegetation will have different spectral reflectance values). 

Classification is basically a method which puts all these 50 values into 1 class of vegetation. So in general classification can be defined as the process of grouping all the pixels of an image into a specified number of classes.

Primarily there are two types of classification,

Supervised Classification: Discussed in Supervised Classification video in the blog.

Unsupervised Classification: This is the simplest way of classifying an image, where human intervention is minimum. Here the user will just define the number of classes and there after we will not do any sort of supervision. System will classify the image based on the DN of the pixels into the number of classes defined by the user. A general comment may be made that, the DNs having same and close by values will be clubbed into one class. However the entire process that happens in the background is not so simple, it also varies slightly based on the re-sampling method selected.

Below is the video on classification if an image using ERDAS Imagine.

Notes and Tips:

• There are possibilities of mis-classification, for example, a portion of vegetation getting classified under the class water. If you find such a case, one method of addressing it to some level is to increase the number of classes. With this, you may end up having two classes of vegetation but likelihood of mis-classification will be addressed to some extent. While preparing map where you have more than one class for any feature, you can assign same color to both the classes and keep only one class in the legend in the map.
• Use unsupervised classification when you are looking for less number of classes. If you are looking for more number of classes, like more than 8 or 10, it is advisable to used supervised classification.