In supervised classification, you must rely on your own pattern recognition skills and knowledge of the data in determining the statistical criteria (signatures) for data classification. To select reliable training sites, you should have some information, either spatial or spectral, about the pixels that you want to classify.
The location of a specific characteristic, such as a land cover type, may be known through reports on ground truth. Ground truthing refers to the acquisition of knowledge about the study area from field-work analysis, aerial photography, or personal experience. Ground truth data is considered to be the most accurate (true) data available about the area you want to study and should be collected at the same time as the remotely-sensed data, so that the data corresponds as much as possible.
Sometimes, ground truth data may not be accurate, due to errors, inaccuracies, and human error. Global positioning system (GPS) receivers are useful in conducting better ground truth studies and collecting training sites.
© PCI Geomatics Enterprises, Inc.®, 2026. All rights reserved.