We first classified the image acquired in 2006 by using the maximum likelihood classifier (Richards and Jia 1999) and five training area sets corresponding to: forest, pasture, bare soil, urban area, and cultivated land cover classes.
Several studies for higher spectral resolution (e.g., 60 channels in [18, 19]) used synthetic data which often favor a particular (such as maximum likelihood) classifier, by virtue of (Gaussian) data construction.
A pixel-based supervised classification with maximum likelihood classifier was used to classify images.
Traditional pixel-based classification methods, such as Maximum Likelihood Classifier (MLC), Spectral Angle Mapper (SAM), Minimum Distance Classifier (MDC), analyze data without incorporating spatial information.
Then, images were classified at pixel level using supervised image classification with maximum likelihood classifier algorithm.
Traditional classification algorithms, such as maximum likelihood classifier, back propagation neural network classifier, are also involved for a comparison purpose.
Using a maximum likelihood classifier, vegetation communities were classified into five classes (successional stages) of grass, grass shrub, shrub, tree shrub, and forest.
Then we classify the images using Maximum Likelihood Classifier (MLC) and Support Vector Machines (SVM) classifier.
All combined bands were classified using a supervised maximum likelihood classifier.
The proposed methodology significantly increased the classification accuracy achieved with a spectral maximum likelihood classifier (ML).
Traditionally the maximum likelihood classifier is used to obtain thematic maps in land use.
