Tree-structured belief networks as models of images

Xiaojuan Feng, C.K.I Williams

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

In this paper we deal with the use the tree-structured belief network (TSBN) as a prior model in segmenting a natural image into a number of predefined classes. The TSBN was trained using the EM algorithm based on a set of training label images. The average log likelihood (or bit rate) of a test set of images shows that the learned TSBN is a better model for images than models based on independent blocks of varying sizes. We also analyze the relative advantages obtained by modelling correlations at different length scales in the tree.
Original languageEnglish
Title of host publicationArtificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470)
PublisherIET
Pages31-36
Number of pages5
ISBN (Print)0-85296-721-7
DOIs
Publication statusPublished - 1 Jan 1999

Keywords / Materials (for Non-textual outputs)

  • tree-structured belief network
  • EM algorithm
  • average log likelihood
  • image coding
  • learning
  • image segmentation

Fingerprint

Dive into the research topics of 'Tree-structured belief networks as models of images'. Together they form a unique fingerprint.

Cite this