Call of Papers for Current Volume **************** OnLine Submission of Paper

Volume & Issue no: Volume 3, Issue 10, October 2014

_____________________________________________________________________________

Title:
Impact of features on classification accuracy of IRS LISS-III images using artificial neural network
Author Name:
Mr.Anand Upadhyay, Dr (Mr.) Santosh Kumar Singh , Mr. Vipin. G. Shukla
Abstract:
ABSTRACT The proposed research paper uses the artificial neural network with back propagation of error is used to classify the LISS-III satellite images. It is a multi-spectral images which are stacked together and there different feature are used for the classification. In this classification the comparative study is performed on two different types of training sets which are used for the classification training. The First training set consist of the R, G, B colour value of the image in this case accuracy and kappa coefficient was 95% and 0.9331 respectively. Second training set consist of R, G, B, mean, mode, median, variance and standard deviation of colour feature and in this case the accuracy and kappa coefficient was 97% and 0.9652 respectively. So after this study and comparative analysis it is observed and concluded that there is the impact of features on the classification. If the number features are less then there is fall in the classification accuracy but increase in the classification accuracy with respect to increase in the number of features in the training sets. Keywords:- LISS-III satellite Image, mean, mode, median, variance, standard deviation, neural network, and classification.
Cite this article:
Mr.Anand Upadhyay, Dr (Mr.) Santosh Kumar Singh , Mr. Vipin. G. Shukla , " Impact of features on classification accuracy of IRS LISS-III images using artificial neural network" , International Journal of Application or Innovation in Engineering & Management (IJAIEM) , Volume 3, Issue 10, October 2014 , pp. 311-317 , ISSN 2319 - 4847.
Full Text [PDF]                           Back to Current Issue