Merging classes after supervised classification
After you have performed supervised classification you may want to merge some of the classes together. This may be because you have features which the classification algorithm cannot discern, such as different types of forest. If you are not really interested in that level of detail, you can group deciduous and evergreen together into forest. A classification schema is used to organize all of the features in your imagery into distinct classes. They are often hierarchical, meaning that you may have a class of forests with sub-classes for evergreen and deciduous. Select the Classification Schema that was used to classify your data. The default schema that is included is from the National Land Cover Dataset (NLCD) which is focused on North America. You can also generate a schema from training samples or from a classified raster. If you want to create a custom schema, select the simple default schema which you can then edit from the Training Samples Manager.
In the table, on the left column, you have the Old Class. If you want to merge classes, use the drop-down list from the New Class to choose which class to merge it to.
As you are merging classes, you will want to see the underlying imagery to verify that the New Class make sense. Press the L key to toggle on and off the transparency of the classified image. If you need to change an entire class you can do that here, but you are limited to the classes which are the parent classes in your schema. For example, you can change deciduous to forest, but you can't change deciduous to water on this page. To make those kinds of edits, or to change individual features, you will need to use the Reclassifier.