0 ×

Contour Detector (deprecated)

KNIME Image Types and Nodes version 1.8.3.202012050717 by University of Konstanz

Detects nearly convex structures from a 'probability image' (where pixels of high intensity are likely to be part of part contour). (Deprecation: Will be replaced in future release!).

Options

Radius
The maximum radius the objects to be detected can have.
Angles
Has impact on the precision of the contours to be detected. But more angles increase the runtime.
Line variance
The value one is usually appropriate.
Overlap
Determines how much the detected objects are allowed to overlap. If two objects overlap more the specified, only the one with the higher score will be kept.
Minimal score
The minimal allowed score (between 0 and 1). All objects below that score will be disregarded.
Minimal area
Objects with a smaller area will be disregarded as well.
Distance equidistant seeding points
The distance between the seeding points over the image. The lower the distance, the more seeding points will be used causing more calculations. A good choice is the half size of the objects to be detected.
Smooth contour
Smoothes the contours by removing little perturbations.

Input Ports

Icon
Source Image and Seeds

Output Ports

Icon
Detected Segments

Best Friends (Incoming)

Best Friends (Outgoing)

Installation

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

KNIME 4.3

A zipped version of the software site can be downloaded here.

You don't know what to do with this link? Read our NodePit Product and Node Installation Guide that explains you in detail how to install nodes to your KNIME Analytics Platform.

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. Browse NodePit from within KNIME, install nodes with just one click and share your workflows with NodePit Space.

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.