The authors know a cluster is a collection of similar objects situated together and are divergent to other cluster objects. In this manuscript, they establish divisive based multi-view point clustering that is based on different similarity measures. With multiple viewpoints, more informative measurement of similarity could be accomplished. Two criterion functions for document clustering are proposed based on this new measure they are, inter cluster and intra-cluster relation between objects. The previous clustering process focused on hierarchical clustering of multi-view point documents, which are not spotlighted on sparse and high dimensional data.