Share Email Print

Proceedings Paper

Image visualization based on MPEG-7 color descriptors
Author(s): Thomas Meiers; H. Czernoch-Peters; L. Ihlenburg; Thomas Sikora
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper we address the user-navigation through large volumes of image data. A similarity-measure based on MPEG-7 color histograms is introduced and Multidimensional Scaling concepts are employed to display images in two dimensions according to their mutual similarities. With such a view the user can easily see relations and color similarity between images and understand the structure of the data base. In order to cope with large volumes of images a modified version of k-means clustering technique is introduced which identifies representative image samples for each cluster. Representative images (up to 100) are then displayed in two dimensions using MDS structuring. The modified clustering technique proposed produces a hierarchical structure of clusters--similar to street maps with various resolutions of details. The user can zoom into various cluster levels to obtain more or less details if required. The results obtained verify the attractiveness of the approach for navigation and retrieval applications.

Paper Details

Date Published: 30 May 2000
PDF: 9 pages
Proc. SPIE 4067, Visual Communications and Image Processing 2000, (30 May 2000); doi: 10.1117/12.386687
Show Author Affiliations
Thomas Meiers, Heinrich-Herz-Institut fuer Nachrichtentechnik Berlin GmbH (Germany)
H. Czernoch-Peters, Heinrich-Herz-Institut fuer Nachrichtentechnik Berlin GmbH (Germany)
L. Ihlenburg, Heinrich-Herz-Institut fuer Nachrichtentechnik Berlin GmbH (Germany)
Thomas Sikora, Heinrich-Herz-Institut fuer Nachrichtentechnik Berlin (Germany)

Published in SPIE Proceedings Vol. 4067:
Visual Communications and Image Processing 2000
King N. Ngan; Thomas Sikora; Ming-Ting Sun, Editor(s)

© SPIE. Terms of Use
Back to Top