احمد کشاورز

Clusters of remote sensing images are very difficult due to the high noise levels of these images. This is a big deal for larger images. In this paper, a fuzzy clustering method is proposed for these images, in which mathematical morphology and middle filtering are used. Mathematical morphology is a method for maintaining boundaries and analyzing and processing geometric structures. Noise can also be stopped easily by math morphology. Thus, using morphological operators, the remote sensing image is improved and the boundaries between the different regions of the image are maintained. Also, using the median filter, you can reduce the noise remaining in the image after fuzzy clustering as much as possible. The results of testing the proposed algorithm on a sample of remote sensing image and comparing it with the current methods of fuzzy clustering indicate the superiority of the proposed algorithm.