The remote is the widely used technology for monitoring the different resources available on earth surface from remote location. It is very important to interpret the different resources with the help of the satellite images. So, the purpose of this research paper is to classify the IRS P-6 LISS-III satellite image using the artificial neural network. The artificial neural network uses the supervised learning for the classification of the LISS-III satellite image. Here, the pixel based classification method is adopted for the classification of the LISS-III image. The proposed classifier is implemented using the Matlab 2010.The LISS-III satellite image of Mumbai region is used for training and testing the classifier. In the proposed paper the accuracy of classifier is calculated using the confusion matrix and Kappa coefficient, apart from the implementation of the artificial neural network here the different comparative study related to the impact of the number of hidden layers and number of the neurons is also performed.
[1]
Demetris Stathakis,et al.
Satellite image classification using granular neural networks
,
2006
.
[2]
Mohammad Reza Mobasheri,et al.
Road and Tunnel Extraction from SPOT Satellite Images Using Neural Networks
,
2013
.
[3]
Mohamad Awad,et al.
An Unsupervised Artificial Neural Network Method for Satellite Image Segmentation
,
2010,
Int. Arab J. Inf. Technol..
[4]
Robert C. Weih,et al.
OBJECT-BASED CLASSIFICATION VS . PIXEL-BASED CLASSIFICATION : COMPARITIVE IMPORTANCE OF MULTI-RESOLUTION IMAGERY
,
2010
.
[5]
Yun Zhang,et al.
Very High Resolution Satellite Image Classification Using Fuzzy Rule-Based Systems
,
2013,
Algorithms.