Classification and Pattern Recognition geoprocessing functions

Available with Spatial Analyst license.

The geoprocessing functions in the Classification and Pattern Recognition category can be used to perform classification and regression analysis workflows, including accuracy assessment. Capabilities include multispectral image segmentation, training sample generation and evaluation, pixel and object-oriented machine learning classification, and quantitative accuracy assessment of results.

An important input is the classification training sample file, produced using the Generate Training Samples From Seed Points function, or using the tools in the Training Samples Manager pane.

Geoprocessing functions in the Classification and Pattern Recognition category

Geoprocessing function	Description
Classify Raster	Classifies a raster dataset based on an Esri classifier definition file (.ecd) 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 must match the inputs used to generate the required .ecd file.
Compute Confusion Matrix	Computes a confusion matrix with errors of omission and commission and derives a kappa index of agreement, Intersection over Union (IoU), and an overall accuracy between the classified map and the reference data.
Compute Segment Attributes	Computes a set of attributes associated with the segmented image. The input raster can be a single-band or 3-band, 8-bit segmented image.
Create Accuracy Assessment Points	Creates randomly sampled points for postclassification accuracy assessment.
Generate Training Samples From Seed Points	Generates training samples from seed points, such as accuracy assessment points or training sample points. A typical use case is generating training samples from an existing source, such as a thematic raster or a feature class.
Inspect Training Samples	Estimates the accuracy of individual training samples. The cross validation accuracy is computed using the previously generated classification training result in an .ecd file and the training samples. Outputs include a raster dataset containing the misclassified class values and a training sample dataset with the accuracy score for each training sample.
Linear Spectral Unmixing	Performs subpixel classification and calculates the fractional abundance of different land-cover types for individual pixels.
Predict Using Regression Model	Predicts data values using the output from the Train Random Trees Regression Model tool.
Remove Raster Segment Tiling Artifacts	Corrects segments or objects cut by tile boundaries during the segmentation process performed as a raster function. This tool is helpful for some regional processes, such as image segmentation, that have inconsistencies near image tile boundaries. This processing step is included in the Segment Mean Shift tool. It should only be used on a segmented image that was not created from that tool.
Segment Mean Shift	Groups adjacent pixels that have similar spectral characteristics into segments.
Train Iso Cluster Classifier	Generates an Esri classifier definition file (.ecd) using the Iso Cluster classification definition.
Train K-Nearest Neighbor Classifier	Generates an Esri classifier definition file (.ecd) using the K-Nearest Neighbor classification method.
Train Maximum Likelihood Classifier	Generates an Esri classifier definition file (.ecd) using the Maximum Likelihood Classifier (MLC) classification definition.
Train Random Trees Classifier	Generates an Esri classifier definition file (.ecd) using the Random Trees classification method.
Train Random Trees Regression Model	Models the relationship between explanatory variables and a target dataset using random trees analysis.
Train Support Vector Machine Classifier	Generates an Esri classifier definition file (.ecd) using the Support Vector Machine (SVM) classification definition.
Update Accuracy Assessment Points	Updates the Target field in the attribute table to compare reference points to the classified image.