Abstract
Feature vectors that are used to represent images exist in a very high dimensional space. Usually, a parametric characterization of the distribution of this space is impossible. It is generally assumed that the features are able to locate visually similar images close in the feature space so that non-parametric approaches, like the k-nearest neighbor search, can be used for retrieval.
This paper introduces a graph-theoretic approach to image retrieval by formulating the database search as a graph clustering problem to increase the chances of retrieving similar images by not only ensuring that the retrieved images are close to the query image, but also adding another constraint that they should be close to each other in the feature space. Retrieval precision with and without clustering are compared for performance characterization. The average precision after clustering was 0.78, an improvement of 6.85% over the average precision before clustering.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
S. Aksoy and R. M. Haralick. Textural features for image database retrieval. In Proc. of IEEE Workshop on CBAIVL, in CVPR’98, pages 45–49, June 1998.
S. Aksoy, “Textural features for content-based image database retrieval,” Master’s thesis, University of Washington, Seattle, WA, June 1998.
C. Carson et al.. Color-and texture-based image segmentation using EM and its application to image querying and classification. submitted to PAMI.
P. Felzenszwalb and D. Huttenlocher. Image segmentation using local variation. In Proc. of CVPR, pages 98–104, June 1998.
B. Huet and E. Hancock. Fuzzy relational distance for large-scale object recognition. In Proc. of CVPR, pages 138–143, June 1998.
L. G. Shapiro and R. M. Haralick. Decomposition of two-dimensional shapes by graph-theoretic clustering. IEEE PAMI, 1(1):10–20, January 1979.
J. Shi and J. Malik. Normalized cuts and image segmentation. In Proc. of CVPR, pages 731–737, June 1997.
Zhenyu Wu and Richard Leahy. An optimal graph theoretic approach to clustering: Theory and its application to image segmentation. IEEE PAMI, 15(11):1101–1113, November 1993.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Aksoy, S., Haralick, R.M. (1999). A Graph-Theoretic Approach to Image Database Retrieval. In: Huijsmans, D.P., Smeulders, A.W.M. (eds) Visual Information and Information Systems. VISUAL 1999. Lecture Notes in Computer Science, vol 1614. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48762-X_43
Download citation
DOI: https://doi.org/10.1007/3-540-48762-X_43
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66079-8
Online ISBN: 978-3-540-48762-3
eBook Packages: Springer Book Archive