Similarity Search in High-Dimensional Vector Spaces
作者： Roger Weber
DOI:
关键词:
摘要: This dissertation addresses the problem of identifying most similar objects in a database given set reference and features. It investigates so-called "Curse Dimensionality", presents an organization for NN-Search ("Nearest Neighbour Search") optimized high-dimensional spaces - "Vector Approximation File" (VA-File). The text shows superiority VA-File theoretically through experiments. is also discussed with to approximate search parallel cluster workstations. dissertaion provides indexing technique that allows interactive-time similarity even huge databases.
amazon.com参考文章(180)
Hans-Jörg Schek, Roger Weber, A Distributed Image-Database Architecture for Efficient Insertion and Retrieval. Multimedia Information Systems. pp. 48- 55 ,(1999)
Masao Sakauchi, Yutaka Ohsawa, The BD-Tree - A New N-Dimensional Data Structure with Highly Efficient Dynamic Characteristics. ifip congress. pp. 539- 544 ,(1983)
Stefan Berchtold, H. P Kriege, Daniel A. Keim, C. B Ohm, A Cost Model For Nearest Neighbour Search symposium on principles of database systems. ,(1997)
Andrew Chi-Chih Yao, F. Frances Yao, A General Approach to d-Dimensional Geometric Queries (Extended Abstract) symposium on the theory of computing. pp. 163- 168 ,(1985)
Joseph M. Hellerstein, Jeffrey F. Naughton, Avi Pfeffer, Generalized Search Trees for Database Systems very large data bases. pp. 101- 112 ,(1995)
Paolo Ciaccia, Marco Patella, Bulk Loading the M-tree ,(2001)
Rudolf Bayer, The Universal B-Tree for multidimensional Indexing ,(1996)
Paolo Ciaccia, Marco Patella, PAC Nearest Neighbor Queries: Using the Distance Distribution for Searching in High-Dimensional Metric Spaces. SEBD. pp. 259- 273 ,(1999)
Susan T. Dumais, LSI meets TREC: a status report text retrieval conference. pp. 137- 152 ,(1992)
Alberto Belussi, Christos Faloutsos, Estimating the Selectivity of Spatial Queries Using the `Correlation' Fractal Dimension very large data bases. pp. 299- 310 ,(1995)