|
|
|
Abstract
Remote sensing data are attractive for deriving land cover information through image classification. A number of parametric and non-parametric classifiers such as the maximum likelihood classifier (MLC) and the artificial neural network (ANN) have been developed and tested successfully on Multispectral data. However, the existing classifiers have shown marked limitations in the classification of hyper spectral images obtained from sensors such as AVIRIS, HYMAP, HYDICE and MODIS. Recently, Support Vector Machine (SVM) has been proposed as an alternative for classification of both multi and hyper spectral data. SVM is a machine-learning algorithm that employs an optimizer to identify an optimal separating hyper plane to discriminate two classes of interest. The results from a few studies on the use of SVM for remote sensing image classification are promising and encouraging. However, there are several issues that need to be considered and investigated before SVM becomes operational in remote sensing applications.
In this paper we present a Multi-class Support Vector Machines (M-SVM) application to remote-Sensing IRS-LISS III image classification. M-SVMs are an n-ary extension of Support Vector Machines (SVM), introduced by Vapnik within the framework of the Statistical Learning Theory and Structural Risk Minimization. In this article we use the M-SVMs in order to classify IRS LISS-III image multi-frequency survey of Khammam District-Andhra Pradesh-INDIA, Pre-processed by a gray-level scaling. Main objective of this work is evaluating the classification performances of M-SVMs in comparison with most frequently employed Neural Network and Maximum Likelihood classifiers. The proposed algorithm returned interesting results with respect to Neural Network and Maximum Likelihood classifiers, having a reliability factor around to 92%.
The aim is to investigate the effect of some factors on the accuracy of SVM classification. The factors considered are selection of multiclass method, choice of the optimizer and the type of kernel function. The results show that among different multiclass methods, optimizers and kernel functions, classification performed with Directed Acyclic Graph multiclass method using the RBF kernel function produced the highest accuracy of 92% when Lagrangian SVM is used as the optimizer.
Keywords: Support vector machines; feature construction; supervised learning; image feature classification; Structural Risk Minimization, Pattern Recognition.
|
|
|