Question

Difference between supervised and unsupervised classification

Answer 1

Unsupervised classification is where the outcomes (groupings of pixels with common characteristics) are based on the software analysis of an image without the user providing sample classes. ... Training sites (also known as testing sets or input classes) are selected based on the knowledge of the user.
Supervised classification is the technique most often used for the quantitative analysis of remote sensing image data. At its core is the concept of segmenting the spectral domain into regions that can be associated with the ground cover classes of interest to a particular application.