The Community for Technology Leaders
Pattern Recognition, International Conference on (2004)
Cambridge UK
Aug. 23, 2004 to Aug. 26, 2004
ISSN: 1051-4651
ISBN: 0-7695-2128-2
pp: 1005-1009
Markus Koskela , Helsinki University of Technology, Finland
Jorma Laaksonen , Helsinki University of Technology, Finland
Erkki Oja , Helsinki University of Technology, Finland
ABSTRACT
Content-based image retrieval (CBIR) addresses the problem of finding images relevant to the users? information needs, based principally on low-level visual features for which automatic extraction methods are available. For the development of CBIR applications, an important issue is to have efficient and objective performance assessment methods for different features and techniques. In this paper, we study the efficiency of clustering methods for image indexing with entropy-based measures. Furthermore, the Self-Organizing Map (SOM) as an indexing method is discussed further and an analysis method which takes into account also the spatial configuration of the data on the SOMis presented. The proposed methods enable computationally light measurement of indexing and retrieval performance for individual image features.
INDEX TERMS
null
CITATION

M. Koskela, J. Laaksonen and E. Oja, "Entropy-Based Measures for Clustering and SOM Topology Preservation Applied to Content-Based Image Indexing and Retrieval," Pattern Recognition, International Conference on(ICPR), Cambridge UK, 2004, pp. 1005-1009.
doi:10.1109/ICPR.2004.1334429
93 ms
(Ver 3.3 (11022016))