Abstract | ||
---|---|---|
Nearest-neighbor search (NN-search) plays a key role for content-based retrieval over multimedia objects. However, performance of existing NN-search techniques is not satisfactory with large collections and with high-dimensional representations of the objects. To obtain response times that are interactive, our approach uses a linear algorithm, parallelizes it and works with approximations of the vectors. In more detail, we parallelize NN-search based on the VA-File in a Network of Workstations (NOW). This approach reduces search time to a reasonable level for relatively large collections. The best speedup we have observed is by almost 30 for a NOW with only three components with 900 MB of feature data. But this requires a number of design decisions, in particular when taking notions such as load dynamicity and heterogeneity of components into account. Our first contribution is to systematically describe and evaluate the various design alternatives, e.g., data placement or decomposing queries into subqueries. As another contribution, we predict the speedup and response times for a given setup. |
Year | DOI | Venue |
---|---|---|
1999 | 10.1007/978-94-015-9664-0_15 | State-of-the-Art in Content-Based Image and Video Retrieval [Dagstuhl Seminar, 5-10 December 1999] |
Keywords | Field | DocType |
large multimedia repository,parallel nn-search | Computer science,Linear algorithm,Workstation,Theoretical computer science,Multimedia,Feature data,Speedup | Conference |
Volume | ISBN | Citations |
22 | 1-4020-0109-6 | 0 |
PageRank | References | Authors |
0.34 | 19 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Roger Weber | 1 | 1172 | 144.05 |
Klemens Böhm | 2 | 1549 | 323.08 |
Hans-Jörg Schek | 3 | 3995 | 1366.90 |