Ultrametric Contour Map

UCMs are a extraction system that combines several types of low-level image information into a generic notion of segmentation scale. This system constructs a hierarchical representation of the image boundaries called Ultrametric Contour Map (UCM). Thresholding the resulting UCM (e.g. with a Global Thresholder) with some threshold k provides by definition a set of closed curves, the boundaries of the segmentation at scale k (from http://www.cs.berkeley.edu/~arbelaez/UCM.html).

Options

Maximum Faces Number
Corresponds to the maximal number of segments that can be retrieved from the UCM if thresholded at each available intensity level.
Maximum Face Percent
The maximum size of a segment relative to the size of the biggest segment (in terms of number of pixels).
Minimum Boundary Weight
The minimum average pixel intensity of a boundary separating two segments (faces). All boundaries below this threshold will not be part of the result UCM.
Boundary Label
Name of the label in the incoming labeling which indicates the boundary between other labels.

Column Selection

Column Creation Mode

Mode how to handle the selected column. The processed column can be added to a new table, appended to the end of the table, or the old column can be replaced by the new result

Column Suffix
A suffix appended to the column name. If "Append" is not selected, it can be left empty.
Column Selection
Selection of the columns to be processed.

Input Ports

Icon
Labeled boundaries and image with boundary weights.

Output Ports

Icon
UCM. Thresholding this UCM at level k provides by definition a set of closed boundaries (i.e. using Global Thresholder).

Views

Image Viewer
Another, possibly interactive, view on table cells. Displays the selected cells with their associated viewer if it exists. Available views are:
- Histogram Viewer
-- This viewer shows the histogram of the currently selected image.
- Image Viewer
-- This viewer renders the selected image-cell.
- Labeling View
-- View on a labeling/segmentation
- Combined View
-- A viewer shown when the user selects an interval of rows and columns in the viewer. This viewer combines all images and labelings in the selected interval to one image by rendering them next to each other. Alternatively, the images and labelings can be layed over each other.
- Missing Value Viewer
-- An empty viewer that is shown when the input cell has no value to display.
- XML
-- XML tree
- BigDataViewer
-- A viewer shown when the user selects an interval of rows and columns in the viewer. This viewer combines all images and labelings in the selected interval to one image by rendering them next to each other. Alternatively, the images and labelings can be layed over each other.

Workflows

Links

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.