0 ×

Image Segment Features

KNIME Image Types and Nodes version 1.8.1.202004280557 by University of Konstanz

Calculate features of an image under consideration of a given labeling. e.g.: Calculate each selected feature for each individual segment.

Options

Features

Tamura
  • Calculates 6 Tamura features: Granularity, Contrast, Kurtosis of Directionality Standard Deviation of Directionality, Maximal directionality, Skewness
Segment Geometry
  • Basic geometric properties: e.g. size, perimeter, centroid, circulartiy, convexity, diameter, ...
First order statistics
  • Calculates the moments of the first order statistics. The following features are computed: Min, Max, Mean, Geometric Mean, Sum, Square of Sums, Standard Deviation, Variance, Skewness, Kurtosis, Quantil25, Quantil50, Quantil75, user defined Quantil, Histogram. Please note that the Geometric Mean can only be computed on unsigned datatypes. Invalid calculations (i.e. NaN) result in missing cells.
Haralick
  • Statistical features based on gray-level co-occurrence matrix. Rotation invariance can be reached by averaging over the four directional co-occurrence matrices (activate 'compute average'). See http://murphylab.web.cmu.edu/publications/boland/boland_node26.html for more information.

Segment Settings

Append labels of overlapping segments
If true, the labels of overlapping segments will be appended in an additional column (';'-separated).
Overlapping segments do NOT need to completely overlap
If selected, segments will also be counted as overlapping, if so don't overlap completely.
Append segment information
If selected, additional information of each segment will be add (e.g. bitmask, source labeling, label). Useful, e.g., if the resulting segment table should be composed again to a labeling (e.g. using the GroupBy-node).
Filter on segment labels
Only labels which hold the given rule considered during the calculation.
Filter overlapping segment labels
Only the labels that comply with the specified rules will appear in the list of overlapping labels.

Input Ports

Source image and labeling

Output Ports

Feature table

Best Friends (Incoming)

Best Friends (Outgoing)

Workflows

Installation

To use this node in KNIME, install KNIME Image Processing from the following update site:

KNIME 4.1
Wait a sec! You want to explore and install nodes even faster? We highly recommend our NodePit for KNIME extension for your KNIME Analytics Platform.

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.