Classification Map Regularization

Brief Description

Filters the input labeled image using Majority Voting in a ball shaped neighbordhood.

Tags

Learning, Image Analysis

Long Description

This application filters the input labeled image (with a maximal class label = 65535) using Majority Voting in a ball shaped neighbordhood. Majority Voting takes the more representative value of all the pixels identified by the ball shaped structuring element and then sets the center pixel to this majority label value.
-NoData is the label of the NOT classified pixels in the input image. These input pixels keep their NoData label in the output image.
-Pixels with more than 1 majority class are marked as Undecided if the parameter 'ip.suvbool == true', or keep their Original labels otherwise.

Parameters

• Input and output images (io): This group of parameters allows setting input and output images for classification map regularization by Majority Voting.

  • Input classification image (io.in): The input labeled image to regularize.

  • Output regularized image (io.out): The output regularized labeled image.




• Regularization parameters (ip): This group allows setting parameters for classification map regularization by Majority Voting.

  • Structuring element radius (in pixels) (ip.radius): The radius of the ball shaped structuring element (expressed in pixels). By default, 'ip.radius = 1 pixel'.

  • Multiple majority: Undecided(X)/Original (ip.suvbool): Pixels with more than 1 majority class are marked as Undecided if this parameter is checked (true), or keep their Original labels otherwise (false). Please note that the Undecided value must be different from existing labels in the input labeled image. By default, 'ip.suvbool = false'.

  • Label for the NoData class (ip.nodatalabel): Label for the NoData class. Such input pixels keep their NoData label in the output image. By default, 'ip.nodatalabel = 0'.

  • Label for the Undecided class (ip.undecidedlabel): Label for the Undecided class. By default, 'ip.undecidedlabel = 0'.

  • Process isolated pixels only (ip.onlyisolatedpixels): Only pixels whose label is unique in the neighbordhood will be processed. By default, 'ip.onlyisolatedpixels = false'.

  • Threshold for isolated pixels (ip.isolatedthreshold): Maximum number of neighbours with the same label as the center pixel to consider that it is an isolated pixel. By default, 'ip.isolatedthreshold = 1'.




• Available RAM (Mb) (ram): Available memory for processing (in MB)

• Load otb application from xml file (inxml): Load otb application from xml file

• Save otb application to xml file (outxml): Save otb application to xml file

Limitations

The input image must be a single band labeled image (with a maximal class label = 65535). The structuring element radius must have a minimum value equal to 1 pixel. Please note that the Undecided value must be different from existing labels in the input labeled image.

Authors

OTB-Team

See also

Documentation of the ClassificationMapRegularization application.

Example of use

• Values for GUIs:

• io.in: clLabeledImageQB123_1.tif

• io.out: clLabeledImageQB123_1_CMR_r2_nodl_10_undl_7.tif

• ip.radius: 2

• ip.suvbool: true

• ip.onlyisolatedpixels: true

• ip.nodatalabel: 10

• ip.undecidedlabel: 7

• Command line to execute:

otbcli_ClassificationMapRegularization -io.in clLabeledImageQB123_1.tif -io.out clLabeledImageQB123_1_CMR_r2_nodl_10_undl_7.tif -ip.radius 2 -ip.suvbool true -ip.onlyisolatedpixels true -ip.nodatalabel 10 -ip.undecidedlabel 7