SATELLITE image segmentation, as a main step of remotely-sensed image processing, is often accomplished by clustering when ground truth is not available to provide samples to train a supervised classifier. To solve this problem, here we propose a new purposes approach for fuzzy segmentation error reduction fuzzy logic-based algorithms as well as structural information is utilized in our proposed multi-resolution Fuzzy C-Mean (FCM) clustering algorithm. The results show that the multi resolution based FCM can improve the result of the standard FCM for an unsupervised classification approach.