Semi-Supervised Clustering: Application to Image Segmentation

  • Mário A. T. Figueiredo
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)


This paper describes a new approach to semi-supervised model-based clustering. The problem is formulated as penalized logistic regression, where the labels are only indirectly observed (via the component densities). This formulation allows deriving a generalized EM algorithm with closed-form update equations, which is in contrast with other related approaches which require expensive Gibbs sampling or suboptimal algorithms. We show how this approach can be naturally used for image segmentation under spatial priors, avoiding the usual hard combinatorial optimization required by classical Markov random fields; this opens the door to the use of sophisticated spatial priors (such as those based on wavelet representations) in a simple and computationally very efficient way.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Mário A. T. Figueiredo
    • 1
  1. 1.Instituto de Telecomunicações and Instituto Superior TécnicoTechnical University of LisbonLisboaPortugal

Personalised recommendations