Color Mapping

Brief Description

Maps an input label image to 8-bits RGB using look-up tables.

Tags

Image Manipulation, Image MetaData, Learning, Utilities

Long Description

This application allows one to map a label image to a 8-bits RGB image (in both ways) using different methods.
-The custom method allows one to use a custom look-up table. The look-up table is loaded from a text file where each line describes an entry. The typical use of this method is to colorise a classification map.
-The continuous method allows mapping a range of values in a scalar input image to a colored image using continuous look-up table, in order to enhance image interpretation. Several look-up tables can been chosen with different color ranges.
-The optimal method computes an optimal look-up table. When processing a segmentation label image (label to color), the color difference between adjacent segmented regions is maximized. When processing an unknown color image (color to label), all the present colors are mapped to a continuous label list.
- The support image method uses a color support image to associate an average color to each region.

Parameters

• Input Image (in): Input image filename

• Output Image (out): Output image filename

• Operation (op): Selection of the operation to execute (default is : label to color).

  • Label to color (labeltocolor):

  • Color to label (colortolabel):

    • Not Found Label (op.colortolabel.notfound): Label to use for unknown colors.




• Color mapping method (method): Selection of color mapping methods and their parameters.

  • Color mapping with custom labeled look-up table (custom): Apply a user-defined look-up table to a labeled image. Look-up table is loaded from a text file.

    • Look-up table file (method.custom.lut): An ASCII file containing the look-up table
      with one color per line
      (for instance the line '1 255 0 0' means that all pixels with label 1 will be replaced by RGB color 255 0 0)
      Lines beginning with a # are ignored

  • Color mapping with continuous look-up table (continuous): Apply a continuous look-up table to a range of input values.

    • Look-up tables (method.continuous.lut): Available look-up tables.

      • Red (red):

      • Green (green):

      • Blue (blue):

      • Grey (grey):

      • Hot (hot):

      • Cool (cool):

      • Spring (spring):

      • Summer (summer):

      • Autumn (autumn):

      • Winter (winter):

      • Copper (copper):

      • Jet (jet):

      • HSV (hsv):

      • OverUnder (overunder):

      • Relief (relief):

    • Mapping range lower value (method.continuous.min): Set the lower input value of the mapping range.

    • Mapping range higher value (method.continuous.max): Set the higher input value of the mapping range.

  • Compute an optimized look-up table (optimal): [label to color] Compute an optimal look-up table such that neighboring labels in a segmentation are mapped to highly contrasted colors. [color to label] Searching all the colors present in the image to compute a continuous label list

    • Background label (method.optimal.background): Value of the background label

  • Color mapping with look-up table calculated on support image (image):

    • Support Image (method.image.in): Support image filename. For each label, the LUT is calculated from the mean pixel value in the support image, over the corresponding labeled areas. First of all, the support image is normalized with extrema rejection

    • NoData value (method.image.nodatavalue): NoData value for each channel of the support image, which will not be handled in the LUT estimation. If NOT checked, ALL the pixel values of the support image will be handled in the LUT estimation.

    • lower quantile (method.image.low): lower quantile for image normalization

    • upper quantile (method.image.up): upper quantile for image normalization




• 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 segmentation optimal method does not support streaming, and thus large images. The operation color to label is not implemented for the methods continuous LUT and support image LUT.
ColorMapping using support image is not threaded.

Authors

OTB-Team

See also

ImageSVMClassifier

Example of use

• Values for GUIs:

• in: ROI_QB_MUL_1_SVN_CLASS_MULTI.png

• method: custom

• method.custom.lut: ROI_QB_MUL_1_SVN_CLASS_MULTI_PNG_ColorTable.txt

• out: Colorized_ROI_QB_MUL_1_SVN_CLASS_MULTI.tif

• Command line to execute:

otbcli_ColorMapping -in ROI_QB_MUL_1_SVN_CLASS_MULTI.png -method custom -method.custom.lut ROI_QB_MUL_1_SVN_CLASS_MULTI_PNG_ColorTable.txt -out Colorized_ROI_QB_MUL_1_SVN_CLASS_MULTI.tif