A parallel similarity search in high dimensional metric space using M-tree

In this study, parallel implementation of M-tree to index high dimensional metric space has been elaborated and an optimal declustering technique has been proposed. First, we have defined the optimal declustering and developed an algorithm based on this definition. Proposed declustering algorithm considers both object proximity and data load on disk/processors by executing a k-NN or a range query for each newly inserted objects. We have tested our algorithm in a database containing randomly chosen 1000 image's color histograms with 32 bins in HSV color space. Experimentation showed that our algorithm produces a very near optimal declustering.