PASDS Plus PPAT Indexing Method for Multimedia Data

Abstract

Indexing and query multimedia data is a challenging problem due to the high dimension of multimedia data. Clustering-based indexing structures are quite efficient for high-dimensional data indexing. Unfortunately, clustering-based indexing structures are normally static, and the whole structures have to be rebuilt after inserting new data. To resolve this issue, a two-level indexing method, called PASDS plus PPAT method, has been developed in this paper. In the PASDS level, clusters and their subspaces can be partially updated, while the indexing trees within the clusters are able to be partially updated at the PPAT level. By choosing proper number of children nodes, the proposed method can balance query accuracy and indexing efficiency. From experiments, the PASDS plus PPAT method is very efficient for updating clusters and inner indexing structures for newly inserted data, while its query accuracy and query time are almost the same with similar dynamic indexing methods.