Affordable Access

Publisher Website

Unsupervised learning of a finite discrete mixture: Applications to texture modeling and image databases summarization

Authors
Journal
Journal of Visual Communication and Image Representation
1047-3203
Publisher
Elsevier
Publication Date
Volume
18
Issue
4
Identifiers
DOI: 10.1016/j.jvcir.2007.02.005
Keywords
  • Multinomial Dirichlet
  • Finite Mixture Models
  • Maximum Likelihood
  • Em
  • Semantic Features
  • Image Retrieval
  • Vistex
  • Cooccurrence Matrix
Disciplines
  • Computer Science
  • Linguistics

Abstract

Abstract This paper presents an unsupervised learning algorithm for fitting a finite mixture model based on the Multinomial Dirichlet distribution (MDD). This mixture is particularly useful for modeling discrete data (vectors of counts). The algorithm proposed is based on the expectation maximization (EM) approach. This mixture is used to improve image databases categorization by integrating semantic features and to produce a new texture model. For the texture modeling problem, the results are reported on the Vistex texture image database from the MIT Media Lab.

There are no comments yet on this publication. Be the first to share your thoughts.