hyperspectral.labeler.AutomationAlgorithm Class

Namespace: hyperspectral.labeler

Interface for algorithm automation in ground truth labeling of spectral image

Since R2026a

Description

Add-On Required: This feature requires the Hyperspectral Imaging Library for Image Processing Toolbox add-on.

The hyperspectral.labeler.AutomationAlgorithm class specifies the interface for defining custom automation algorithms to run in the Spectral Image Labeler app. Classes that inherit from the AutomationAlgorithm interface can be used with the automation process of the app to generate ground truth labels.

To use a class inherited from the AutomationAlgorithm interface from within the Spectral Image Labeler app, perform these steps.

• Create a +hyperspectral/+labeler package directory within a folder that is already on the MATLAB path. For example, if the folder /local/MyProject is on the MATLAB path, then you can create a +hyperspectral/+labeler folder hierarchy using these commands.

  projectFolder = fullfile("local","MyProject");
  automationFolder = fullfile("+hyperspectral","+labeler");
  mkdir(projectFolder,automationFolder)

• Save the class file to the +hyperspectral/+labeler package directory. Saving the file to the package directory is required to use your custom algorithm from within the Spectral Image Labeler app.

The hyperspectral.labeler.AutomationAlgorithm class is a handle class.

Class Attributes

Abstract

true

For information on class attributes, see Class Attributes.

Note

The Hyperspectral Imaging Library for Image Processing Toolbox™ requires desktop MATLAB^®, as MATLAB Online™ and MATLAB Mobile™ do not support the library.

Properties

Name — Automation algorithm name

character vector

Automation algorithm name, specified as a character vector.

Attributes:

GetAccess	public
Abstract	true
Constant	true
NonCopyable	true

Description — Automation algorithm description

character vector

Automation algorithm description, specified as a character vector.

Attributes:

GetAccess	public
Abstract	true
Constant	true
NonCopyable	true

SupportsHypercube — Algorithm support for hypercube objects

true | false

Algorithm support for hypercube objects, specified as true or false. Specify a value to SupportsHypercube to indicate whether your custom algorithm supports hypercube objects as input.

Attributes:

GetAccess	public
Abstract	true
Constant	true
NonCopyable	true

SupportsMulticube — Algorithm support for multicube objects

true | false

Algorithm support for multicube objects, specified as true or false. Specify a value to SupportsMulticube to indicate whether your custom algorithm supports multicube objects as input.

Attributes:

GetAccess	public
Abstract	true
Constant	true
NonCopyable	true

Instruction — Algorithm instructions displayed in app

cell array of character vectors

Algorithm instructions displayed in app, specified as a cell array of character vectors. You must specify Instruction as a cellstr, with each string representing a separate direction. You can read the instructions by selecting Algorithm Instruction on the Automate tab of the Spectral Image Labeler app toolstrip.

Attributes:

GetAccess	public
Abstract	true
Constant	true
NonCopyable	true

Methods

Public Methods

Clients of an AutomationAlgorithm implement these user-defined functions to define execution of the algorithm. For an example on creating your own automation algorithm, see Segment Hyperspectral Image Using Segment Anything Model in Spectral Image Labeler.

settingsDialog	Display automation algorithm settings (optional)
run	Run label automation algorithm on spectral image

Version History

Introduced in R2026a