Comparison of Three Classification Algorithms (ANN, SVM and Maximum Likelihood) for Preparing Land Use Map (Case Study: Abolabbas Basin)

One of the most important tasks of remote sensing technology is to producing land use maps. In this study, in order to produce land use map of abolabbas basin, landsat satellite image of TM scanner acquired on 01 June 2009 were employed. the image classified by using three-layer perceptron neural network, support vector machine with the radial basis kernel function and Maximum Likelihood algorithm. So, The performance of different classification algorithms in producing land use maps were investigated using overall accuracy and kappa coefficient. Results showed that Nonparametric algorithms such as artificial neural network (with 95.8% overall accuracy and 0.95 kappa coefficient) and support vector machine with the radial basis kernel function (with 95.8% overall accuracy and 0.94 Kappa coefficient) with the same performance were better than the third method which is Parametric maximum likelihood algorithm (with 93.7% overall accuracy and 0.91 Kappa coefficient). Overall, this study showed that three classification algorithms, neural network, support vector machine and maximum likelihood are capable to generate land use maps with high accuracy.