Marketplace

K-means Clustering

This block takes an AOI clipped image and runs a simple classification procedure. The classification is a simple unsupervised K-means clustering in the color space of the image. The number of clusters and other parameters can be specified for the classification.

Description

K-means Clustering provides the simple unsupervised classification algorithm K-Means clustering. It creates a set number of classes in each dataset and classify each pixel in one of this classes.

The source code is published as Free Software / Open Source (MIT License) here.

General InformationDescription
Block Typeprocessing
Supported Input TypesGeoTIFF
Output formatGeoTIFF
Resolutionidentical to the input

More information

Check the block's documentation here for more information.

Capabilities

Input Capabilities

raster
up42_standard
format
GTiff

Output Capabilities

raster
up42_standard
dtype
uint8
format
GTiff
resolution
> (Propagated)

End User License Agreement

View the End User License Agreement conditions in a new tab.