Setting up and running Supervised Classification

To run a supervised classification, you must have a training data set for Object Analyst to learn from and create a classification model that is used to predict the class membership of the population.

To set up and run a supervised classification

In the Object Analyst window, in the list under Operation, select Supervised classification.
The display is refreshed to show the settings for supervised classification.
Under Vector Layer and Fields, click Select, and then in the Vector Layer and Field Layer Selection window, do the following:
1. In the File box, type or select the file you want.
  If the file you want does not appear in the list, click Browse, and then select the file you want.
2. In the Layer box, type or select the layer you want.
3. In the Fields box, click one or more of the fields you want or, to select all the fields, click Select All.
  A check mark appears beside each field you select.
4. Click OK.
In the Training field list, select the field you want to use.
Typically, this is the field you created while editing training sites.
In the Output class field list, select the field to use during processing.
The field you select will be added to the attribute table of the selected layer to store the predicted results of the classification, which you can then view in Attribute Manager. Whenever you run a classification subsequently with this field specified, the existing value will be overwritten.
In the Classifier list, click one of the following:
- SVM - Support vector machine
- RT - Random trees
If you want to save the training model, select the Save training model check box, and then in the File box, type a path and file name or, to select a file, click Browse.
Important: If you intend to later run a batch classification, make sure you select to create and save the training-model file. You will need the file when you run the batch classification.
Do one of the following:
- To add the operation to the Process Canvas box, click Add.
- To add the operation to the canvas and run the process, click Add and Run.