Cluster analysis of earth remote sensing data
Authors:
- 1 April 2010
- journal article
- Published by Allerton Press in Optoelectronics, Instrumentation and Data Processing
- Vol. 46 (2) , 149-155
Abstract
A system of cluster analysis (unsupervised classification) for Earth remote sensing data is considered. The system is represented by three methods: the K-means method, the mode analysis of multidimensional histograms, and a hybrid method which combines the mode analysis of multidimensional histograms with their subsequent hierarchical grouping.Keywords
This publication has 7 references indexed in Scilit:
- Controlled classification of Earth remote sensing dataOptoelectronics, Instrumentation and Data Processing, 2008
- Survey of Clustering AlgorithmsIEEE Transactions on Neural Networks, 2005
- Pattern Recognition2001
- An empirical comparison of four initialization methods for the K-Means algorithmPattern Recognition Letters, 1999
- On finding the number of clustersPattern Recognition Letters, 1999
- Least squares quantization in PCMIEEE Transactions on Information Theory, 1982
- A non-parametric clustering scheme for landsatPattern Recognition, 1977