Module: Adaptive Thresholding ()

Description:

Binarization transforms a gray level image into a binary image. This method is used when the relevant information in the gray level image corresponds to specific gray level interval. In the binary image the pixels of interest are set to 1, and to 0 for all other pixels (the background).

This module computes the threshold of a grayscale image, given a label image corresponding to the pre-segmentation of the original image. Instead of giving two fixed values for the thresholding, the user chooses two representative measures (e.g., the 10th and the 90th percentile of the histogram). The min and max threshold values are dynamically computed for each label and gives an individual thresholding on them.

See also: Auto Thresholding.

Connections:

Input Grayscale Image [required]
The input gray image to be thresholded. Supported types include: Grayscale images (Uniform Scalar Field).

Input Label Image [required]
The image is the pre-segmentation of the original image. Supported types include: Label images (Uniform Label Field).

Ports:

Interpretation

This port specifies whether the input will be interpreted as a 3D volume or a stack of 2D images for processing.

• "3D": the module configuration is set to 3D. The image will be processed as a whole in 3D.
• "XY planes": the module configuration is set to 2D. The image will be processed slice by slice.

Measure 1

This port sets the first individual measure.

Measure 2

This port sets the second individual measure.