Unsupervised image-set clustering using an information theoretic framework

IEEE Trans Image Process. 2006 Feb;15(2):449-58. doi: 10.1109/tip.2005.860593.

Abstract

In this paper, we combine discrete and continuous image models with information-theoretic-based criteria for unsupervised hierarchical image-set clustering. The continuous image modeling is based on mixture of Gaussian densities. The unsupervised image-set clustering is based on a generalized version of a recently introduced information-theoretic principle, the information bottleneck principle. Images are clustered such that the mutual information between the clusters and the image content is maximally preserved. Experimental results demonstrate the performance of the proposed framework for image clustering on a large image set. Information theoretic tools are used to evaluate cluster quality. Particular emphasis is placed on the application of the clustering for efficient image search and retrieval.

Publication types

  • Evaluation Study

MeSH terms

  • Algorithms*
  • Artificial Intelligence*
  • Cluster Analysis*
  • Databases, Factual*
  • Image Enhancement / methods*
  • Image Interpretation, Computer-Assisted / methods*
  • Information Storage and Retrieval / methods*
  • Information Theory
  • Pattern Recognition, Automated / methods*