Available with Spatial Analyst license.
With the Segmentation and Classification tools, you can prepare segmented rasters to use in creating classified raster datasets.
The following table lists the available segmentation and classification tools and provides a brief description of each.
Classify a raster dataset based on an Esri Classifier Definition (.ecd) file and raster dataset inputs.
The .ecd file contains all the information needed to perform a specific type of Esri-supported classification. The inputs to this tool need to match the inputs used to generate the required .ecd file.
Computes a confusion matrix based on errors of omission and commission, then derives a kappa index of agreement between the classified map and data that is considered to be ground truth.
Compute a set of attributes associated with your segmented image. The input raster can be a single-band or 3-band, 8-bit segmented image.
Creates randomly sampled points for post-classification accuracy assessment.
Identify features or segments in your imagery by grouping adjacent pixels together that have similar spectral characteristics. You may control the amount of spatial and spectral smoothing to help derive features of interest.
Generate an Esri classifier definition (.ecd) file using the Iso Cluster classification definition.
Generate an Esri classifier definition (.ecd) file using the Maximum Likelihood Classifier (MLC) classification definition.
Generate an Esri classifier definition (.ecd) file using the Random Trees classification method.
Generate an Esri classifier definition (.ecd) file using the Support Vector Machine (SVM) classification definition.
Updates fields in the attribute table to compare ground truth points to the classified image. It can also update the set of points used for accuracy assessment to reflect changes in the classification scheme or in the ground truth data.