Analysis of Classified Satellite Images using different Neural Networks
Harikrishnan R1, Shivali Amit Wagle2

1Harikrishnan R, Symbiosis Institute of Technology, Symbiosis International Deemed University, Pune (M.H), India.
2Shivali Amit Wagle, Symbiosis Institute of Technology, Symbiosis International Deemed University, Pune (M.H), India.

Manuscript received on 18 June 2019 | Revised Manuscript received on 25 June 2019 | Manuscript published on 30 June 2019 | PP: 379-382 | Volume-8 Issue-5, June 2019 | Retrieval Number: E7129068519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The classification of multispectral satellite images using the various artificial neural network classifiers are discussed in this paper. Various methods have been used in the field of remote sensing that are doing image classification using significant concepts for high performance. The mean, variance and textural features extraction technique is used here. The extracted features are used for training the neural network. The back propagation, radial basis function and self organizing map are used for the classification of the multispectral satellite image. Ensemble techniques of bagging, boosting and Ada-Boosting are used for the same image for classification. The effect of the classification results based on the amount of training data shows that if the network is trained using 25% of the data from the actual size of the data then they are giving better or similar results as compared to the network with 50% of trained network. Parameters like overall accuracy, producer’s accuracy, user’s accuracy and Kappa coefficient are evaluated for the performance of the classifiers.
Keywords: Ensemble Classifiers, Producer’s accuracy, User’s accuracy, Kappa Coefficient.

Scope of the Article: Classification