Clustering is considered an interesting approach for finding similarities in data and putting similar data objects into groups. It finds natural groups presents in the data set. It divides a given data set into a set of clusters. Fuzzy clustering assigns membership to an object which is inversely related to the relative distance of the object to cluster prototype. The resulting membership values do not always correspond well to the degrees of belonging of the data.Rough set are the sets with fuzzy boundaries. In Rough-Fuzzy clustering each cluster is consist of a fuzzy lower approximation and a fuzzy boundary. Each object in lower approximation takes a distinct weight, which is its fuzzy membership value. The lower approximation of a rough cluster contains objects that only belong to that cluster. The upper approximation of a rough cluster contains objects in the cluster which are also members of other clusters. In this approach similarities are described by membership degrees and definite or possible members to a cluster are detected. The Rough-Fuzzy clustering groups the elements in such a way that one object belong to only one cluster otherwise it will form a new cluster