Self-organised maps (SOM) have been widely used for cluster analysis and visualisation purposes in exploratory data mining. In image retrieval applications, SOMs have been used to visualise high-dimensional feature space and build indexing structures. In this paper, we extend the use of SOMs for profiling and comparison of image collections, and present empirical results obtained in collection visualisation, visual and quantitative comparison of collections, and a prototype system implementation.
|Cite as: Deng, D., Zhang, J. and Purvis, M. (2004). Visualisation and Comparison of Image Collections based on Self-organised Maps. In Proc. Australasian Workshop on Data Mining and Web Intelligence (DMWI2004), Dunedin, New Zealand. CRPIT, 32. Purvis, M., Ed. ACS. 97-102. |
(local if available)