Before you can perform a classification or an accuracy assessment, you must have ground-truth data: information collected on location. With ground-truth data, image data can be related to real attributes and materials on the ground. By collecting ground-truth data, remote-sensing data can be calibrated, which aids in the interpretation and analysis of what is being sensed.
With supervised classification, the ground-truth data acts as a training set, which is used by the learning algorithm to generate a classification model. In Object Analyst, you collect training samples for both the supervised classification and accuracy assessment in the same window.
If necessary, you can adjust the minimum percentage threshold. By doing so, objects below the threshold are not updated.
To importing ground-truth points
If the file is not in the list, click Browse, and then select the file you want.
When you view the class name in Attribute Manager, it is prefixed with _T.
When you view the class name in Attribute Manager, it is prefixed with _A.
When you select Majority, you can, if necessary, type or select the percentage weight you want in the box to the right. The default value is 51.
A message appears, showing the point layer you selected and the number of one-to-one matches that occurred, and the number of conflicts.
© PCI Geomatics Enterprises, Inc.®, 2026. All rights reserved.