Fast Approximate Nearest-Neighbor Queries in Metric Feature Spaces by Buoy Indexing
An indexing scheme for solving the problem of nearest neighbor queries in generic metric feature spaces for content-based retrieval is proposed aiming to break the “dimensionality curse”. The basis for the proposed method is the partitioning of the feature dataset into a fixed number of clusters that are represented by single buoys. Upon submission of a query request, only a small number of clusters whose buoys are close to the query object are considered for the approximate query result, cutting down the amount of data to be processed effectively. Results from extensive experimentation concerning the retrieval accuracy are given. The influence of control parameters is investigated with respect to the tradeoff between retrieval accuracy and query execution time.
KeywordsFeature Space Query Point Indexing Scheme Media Object Retrieval Accuracy
Unable to display preview. Download preview PDF.
- 2.Beckmann, N., Kriegel, H.P., Schneider, R., Seeger, B.: The R *-tree: An Efficient and Robust Access Method for Points and Rectangles. Proc. of the ACM SIGMOD Int’l Conf. on Management of Data. Atlantic City, NJ, USA. (1990) 322–332.Google Scholar
- 3.Bow, S.T.: Pattern Recognition and Image Preprocessing. Marcel Dekker, Inc. (1992).Google Scholar
- 4.Chiueh, T.: Content-Based Image Indexing. Proc. of the 20th Int’l Conf. on Very Large Databases. Santiago, Chile. (1994) 582–593.Google Scholar
- 5.Ciaccia, P. and Patella, M. and Zezula P.: M-tree: an Efficient Access Method for Similarity Search in Metric Spaces. Proc. of the 23rd Int’l Conf. on Very Large Databases. Athens, Greece. (1997) 426–435.Google Scholar
- 6.Faloutsos, C., Lin, K.I.: FastMap: A Fast Algorithm for Indexing, Data-Mining and Visualization of Traditional and Multimedia Datasets. Proc. of the ACM SIGMOD Conf. San Jose, CA, USA. (1995) 163–174.Google Scholar
- 7.Guttman, A.: R-tree: A Dynamic Indexing Structure for Spatial Searching. Proc. of the ACM SIGMOD Int’l Conf. on Management of Data. Boston, MA, USA. (1984) 47–57.Google Scholar
- 8.Ng, R., Sedighian, A.: Evaluating Multi-dimensional Indexing Structures for Images Transformed by Principal Component Analysis. Proc. SPIE Vol. 2670. (1996) 50–61.Google Scholar
- 10.Sellis, T., Roussopoulos, N., Faloutsos, C.: The R +-tree: A Dynamic Index for Multidimensional Objects. Proc. 13rd Int’l Conf. on Very Large Data Bases. Brighton, England. (1987) 507–518.Google Scholar
- 11.Stoffel, K., Belkoniene, A.: Parallel k/h-Means Clustering for Large Data Sets. Proc. of the 5th EUROPAR Conf. on Parallel Processing. Toulouse, France. (1999) 1451–1454.Google Scholar
- 12.Vleugels, J., Veltkamp, R.C.: Efficient Image Retrieval through Vantage Objects. Proc. of the 3rd Int’l Conf. onVisual Information Systems. Amsterdam, The Netherlands. (1999) 575–584.Google Scholar
- 13.Volmer, S.: Tracing Images in Large Databases by Comparison of Wavelet Fingerprints. Proc. of the 2nd Int’l Conf. on Visual Information Systems. La Jolla, CA, USA. (1997) 163–172.Google Scholar
- 14.White, D.A., Jain, R.: Similarity Indexing:Algorithms and Performance. Proc. SPIE Vol. 2670. (1996) 65–72.Google Scholar