Journal of Applied Sciences1812-56541812-5662orgz10.3923/jas.2010.636.643IzabateneH. FizaziRabahiR.82010108The satellite observation with a resolution of ten meters provides images of earth surface. The precise spectral information allows a classification of earth objects. Due to some considerations, Markov Random Field has become a common search procedure. Attention has been focused on utilizing the spatial context in image classification; labels are to be assigned to individuals’ pixels or groups of pixels. In this approach, we relied on, among approaches to Markov Random Field to a supervised classification of satellite images. This approach is known as the Multi-Scales model. We use an energy expression according to Potts model.]]>Achab, K., H. Fizazi and B. Sidaoui,2007Bonn, F., R. Caloz and C. Collet,2002Bouman, C.A. and B. Liu,1991Bouman, C.A. and M. Shapiro,1994Derin, H. and H. Elliott,1987Dubes, R., A. Jain, S. Nadabar and C. Chen,1990Iftene, T. and H. Mahi, 1996Kato, Z., J. Zerubia and M. Berthod, 1992Kato, Z., M. Berthod and J. Zerubia, 1993Kato, Z.,1994Kaddar, B. and H. Fizazi,2009Lorette, A., X. Descombes and J. Zerubia, 1998Smits, P.C. and S.G. Dellepiane,1996Polverni, U. and L. Gautret, 2001Rabahi, R. and K. Ismail,2003Rignot, E. and R. Chellappa,1993Iarkani, N. and H. Amel, 2008