JFET_V6_N2_RP1 Mounir Salhi Journal on Future Engineering and Technology 2230 – 7184 6 2 1 9 Classification, Vegetation Indices, Mathematical Morphology, Generalization, IKONOS In this paper, the author present an object-based approach for rural land cover classification from high-resolution multispectral image data that builds upon a pixel-based segmentation. A mathematical morphology algorithm is then implemented to build objects by a generalization technique to facilitate further object-based classification. The imagery used for this study was acquired by the IKONOS commercial remote sensing satellite and consists of four multi- spectral bands. The object-based classifier uses shape and spectral features to determine the final classification of a segmented image. Using these techniques, the object-based classifier is able to identify olive tree fields from farms and impervious surface. November 2010 - January 2011 Copyright © 2011 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=1320