Classification of remote sensing images from urban areas based on fuzzy system

The problem of classification of high-resolution remotely sensed images from urban areas is addressed. This work proposed a new method based on fuzzy system to recognise different areas in a remote sensing image. Previous studies have shown the interest of exploiting the local geometrical information of each pixel to improve the classification. This is performed using the Derivative Morphological Profile (DMP) obtained with a granulometric approach, using opening and closing operators respectively. In this paper, I present an interpretation of the DMP and then explain the fuzzy method which is pixel wise, in which histogram of grey scale image is used to determine which type of membership function has to be used.