Unsupervised image-set clustering using an information theoretic framework

Jacob Goldberger*, Shiri Gordon, Hayit Greenspan

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish
Pages (from-to)449-458
Number of pages10
JournalIEEE Transactions on Image Processing
Volume15
Issue number2
DOIs
StatePublished - Feb 2006

Keywords

  • Hierarchical database analysis
  • Image clustering
  • Image database management
  • Image modeling
  • Information bottleneck (IB)
  • Kullback-Leibler divergence
  • Mixtute of Gaussians
  • Mutual information
  • Retrieval

Fingerprint

Dive into the research topics of 'Unsupervised image-set clustering using an information theoretic framework'. Together they form a unique fingerprint.

Cite this