rasclass: Supervised Raster Image Classification

Software to perform supervised and pixel based raster image classification. It has been designed to facilitate land-cover analysis. Five classification algorithms can be used: Maximum Likelihood Classification, Multinomial Logistic Regression, Neural Networks, Random Forests and Support Vector Machines. The output includes the classified raster and standard classification accuracy assessment such as the accuracy matrix, the overall accuracy and the kappa coefficient. An option for in-sample verification is available.

Version: 0.2.2
Imports: methods, car, nnet, RSNNS, e1071, randomForest
Published: 2016-05-02
DOI: 10.32614/CRAN.package.rasclass
Author: Daniel Wiesmann and David Quinn
Maintainer: Daniel Wiesmann <daniel.wiesmann at tecnico.ulisboa.pt>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
Materials: NEWS
CRAN checks: rasclass results


Reference manual: rasclass.pdf


Package source: rasclass_0.2.2.tar.gz
Windows binaries: r-devel: rasclass_0.2.2.zip, r-release: rasclass_0.2.2.zip, r-oldrel: rasclass_0.2.2.zip
macOS binaries: r-release (arm64): rasclass_0.2.2.tgz, r-oldrel (arm64): rasclass_0.2.2.tgz, r-release (x86_64): rasclass_0.2.2.tgz, r-oldrel (x86_64): rasclass_0.2.2.tgz
Old sources: rasclass archive


Please use the canonical form https://CRAN.R-project.org/package=rasclass to link to this page.