Open map List

[IP3-4-4] Clustering (unsupervised)

Unsupervised methods are defined as the identification of natural groups, or structures, within existing data. Clustering requires only the number of to-be generated classes as an input parameter and assigns spectrally defined classes to an image.

Introduction

The assigned subconcept [IP3-4-4-1] k-Means clustering has been deleted and turned into a Skill for this concept

MacQueen, J., 1967, Some methods for classification and analysis of multivariate observations, Fifth Berkeley Symposium on Mathematics, Statistics and Probability, University of California Press (1967), pp. 281-297

External resources

Campbell, J.B., & Wynne, R.H. (2011). Introduction to remote sensing. Guilford Press, New York-London

Learning outcomes

1604 - Apply k-Means clustering to an image to extract spectrally homogeneous clusters

Apply k-Means clustering to an image to extract spectrally homogeneous clusters

Self assessment

New

Outgoing relations

[IP3-4-4] Clustering (unsupervised) subclassof [IP3-4] Image classification