A Cluster Based Distance Bounding for High Dimensional Indexing+

Clustering is one of the important aspect in data mining. Clustering means similar group of objects. VA-file is a technique to combat the curse of dimensionality and hence necessarily ignores dependencies across dimensions. Existing methods to prune irrelevant clusters are based on bounding hyper spheres or bounding rectangles, whose lack of tightness compromises their efficiency in exact nearest neighbor search. A new cluster-adaptive distance bound based on separating hyper plane boundaries of Voronoi clusters is to complement our cluster based index We propose indexing method to enhance data search and data retrieval.