Classification of Multispectral satellite images

Author

Kar, S.A. ; Kelkar, V.V.

fYear

2013

fDate

23-25 Jan. 2013

Firstpage

1

Lastpage

6

Abstract

This paper is a review of classification of remote sensed Multispectral satellite images. Texture is the frequency of tonal changes on the image. The texture gives the `rough´ or `smooth´ appearance of the image. Higher resolution causes higher spectral variability within a class and lessens the statistical separability among different classes in a traditional pixel-based classification. Several methods of image classification exist and a number of fields apart from remote sensing like image analysis and pattern recognition make use of a significant concept.

Keywords

covariance matrices; geophysical image processing; image classification; radial basis function networks; remote sensing; support vector machines; RBF neural networks; covariance matrix; image analysis; image texture; multispectral satellite image classification; pattern recognition; pixel-based classification; remote sensing; rough appearance; smooth appearance; statistical separability; support vector machine; Classification algorithms; Image classification; Image edge detection; Neural networks; Remote sensing; Training; Vegetation mapping; ISODATA; Mahalanobis; Multi-Layer Preceptron; Radial basis function; Self-organising Map; Support Vector Machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Advances in Technology and Engineering (ICATE), 2013 International Conference on

Conference_Location

Mumbai

Print_ISBN

978-1-4673-5618-3

Type

conf

DOI

10.1109/ICAdTE.2013.6524747

Filename

6524747