SUPERVISED GAUSSIAN MIXTURE MODEL BASED REMOTE SENSING IMAGE CLASSIFICATION

Abstract

Software like ILWIS and GRASS GIS can be employed for remote sensing image processing and geographic information systems applications. The modules of the aforementioned image processing software are based on conventional multi-class classifiers/algorithms such as maximum likelihood classifier. These conventional multi-class classifiers/algorithms are usually written in programming languages such as C, C++, and python. The objective of this research is to experiment the use of the parametric Gaussian mixture model multi-class classifier/algorithm for multi-class remote sensing task, implemented in MATLAB. MATLAB is a programming language just like C, C++, and python. In this research, a computer program implemented in MATLAB is used to experiment the Gaussian mixture model algorithm. Using the supervised classification technique, both simulated and empirical satellite remote sensing data are used to train and test the Gaussian mixture model algorithm. For the purpose of validating the experiment, the resulting classified satellite image is compared with the ground truth data. For the simulated modelling, twenty-five pixels are used for the modelling, out of which six pixels are used for training while nineteen pixels are used for testing. All the nineteen tested pixels are correctly classified. For the empirical modelling, some of the pixels are wrongly classified; the computed overall accuracy is 85.35%; which indicates substantial agreement between the classification result and the reference data.