This paper is of classification of remote sensed Multispectral satellite images using supervised and unsupervised neural networks. Feature extraction techniques like mean, variance and standard deviation are used. 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. The combination of multiple classifiers is done for designing high performance pattern classification systems.

1. Ahsan Ahmad Ursani, Kidiyo Kpalma, Camille C. D. Lelong, and Joseph Ronsin, "Fusion of Textural and Spectral Information for Tree Crop and Other Agricultural Cover Mapping WithVery-High Resolution Satellite Images", IEEE Journal of Selected Topics In Applied Earth Observations and Remote Sensing, Vol. 5, NO. 1, pp 225-235 February 2012
2. Mohamed Anis Loghmari, Mohamed Saber Naceur, and Mohamed Rached Boussema, "A Spectral and Spatial Source Separation of Multispectral Images", IEEE Transactions on Geoscience and Remote Sensing, Vol. 44, NO. 12, pp 3659-3673, December 2006
3. M. H. Batista and V. Haertel, "On the classification of remotes sensing high spatial resolution image data," Int. J. Remote Sens. , vol. 31, pp. 5333–5548, 2010.
4. Q. Yu et al. , "Object-based detailed vegetation classification with airborne high spatial resolution remote sensing imagery," Photogramm. Eng. Remote Sens. , vol. 72, pp. 799–811, 2006.
5. J. Stuckens et al. , "Integrating contextual information with per-pixel classification for improved land cover classification," Remote Sens. Environ. ,vol. 71, pp. 282–296, 2000.
6. J. A. Lozano et al. , "An empirical, comparison of four initialization methods for the K-means algorithm," Pattern Recognit. Lett. , vol. 20, pp. 1027–1040, 1999.
7. E. Blanzieri and F. Melgani, "Nearest neighbor classification of remote sensing images with the maximal margin principle," IEEE Trans. Geosci. Remote Sens. , vol. 46, pp. 1804–1811, 2008.
8. M. Lennon, G. Mercier, M. C. Mouchot, and L. Hubert-Moy, "Spectral unmixing of hyperspectral images with the independent component analysis and wavelet packets," in Proc. IGARSS Conf. , Sydney, Australia, Jul. 9–13, 2001.
9. M. Lennon and G. Mercier, "Quelques applications de l'analyse en composantes indépendantes en imagerie hyperspectrale," in Journée Action Spécifique Séparation de Sources. Paris, France: GDR ISIS, Sep. 2003.
10. M. S. Naceur, M. A. Loghmari, and M. R. Boussema, "The contribution of the sources separation method in the decomposition of mixed pixels," IEEE Trans. Geosci. Remote Sens. , vol. 42, no. 11, pp. 2642– 2653, Nov. 2004.
11. J. F. Cardoso, "Blind signal separation: Statistical principles," Proc. Inst. Electr. Eng. , vol. 9, no. 10, pp. 2009–2025, Oct. 1998.
12. Shivali A. Kar, Vishakha V. Kelkar, "Classification of Multispectral Satellite Images, ICATE 2013, paper identification number 115, pp1-6
13. C. Palaniswami, A. K. Upadhyay and H. P. Maheswarappa, "Spectral mixture analysis for subpixel classification of coconut", Current Science, Vol. 91, No. 12, pp. 1706 -1711, 25 December 2006.
14. Landsat images: http://serc. carleton. edu/
15. Giorgio Giacinto, Fabio Roli,"Ensembles of Neural Networks for Soft Classification of Remote-sensing images"

Multi-layer Preceptron Back Propagation Radial Basis Function Self-organising Map voting Algorithm