Land cover classification using Adaptive Resonance Theory-2

This paper describes the task of land cover classification using Adaptive Resonance Theory 2 (ART 2). Adaptive resonance theory 2 has been used to segment the satellite image. Image segmentation refers to the partition of pixels into homogeneous classes so that items in the same class are as similar...

Full description

Saved in:
Bibliographic Details
Published in2011 International Conference on Electronics, Communication and Computing Technologies pp. 78 - 82
Main Authors Sowmya, B., Thirumaran, A., Aravindh, R., Prasad, A. A.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2011
Subjects
ART2
Earth
Educational institutions
Image color analysis
Image segmentation
Land Cover Classification
Neural Network
Neurons
Satellites
Subspace constraints
Online AccessGet full text
ISBN1457718952
9781457718953
DOI10.1109/ICECCT.2011.6077074

Cover

More Information
Summary:This paper describes the task of land cover classification using Adaptive Resonance Theory 2 (ART 2). Adaptive resonance theory 2 has been used to segment the satellite image. Image segmentation refers to the partition of pixels into homogeneous classes so that items in the same class are as similar as possible and pixels in different classes are as dissimilar as possible. The most basic attribute for segmentation is image intensity for a monochrome image and color components for a color image. Since there are more than 16 million colors available in any given image and it is difficult to analyze the image on all of its colors, the likely colors are grouped together by image segmentation ART 2 has been used for image segmentation. The RGB values of each pixel are found. Depending on the spectral value, the pixels are classified as urban area, bare soil, forest & vegetation and water regions by ART 2.
ISBN:1457718952
9781457718953
DOI:10.1109/ICECCT.2011.6077074