Edinburgh Research Explorer

Combining neural networks and belief networks for image segmentation

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

Original languageEnglish
Title of host publicationNeural Networks for Signal Processing VIII, 1998. Proceedings of the 1998 IEEE Signal Processing Society Workshop
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages393-401
Number of pages9
ISBN (Print)0-7803-5060-X
DOIs
Publication statusPublished - 1 Aug 1998

Abstract

We are concerned with segmenting an image into a number of predefined classes. We show how to fuse together local predictions for the class labels with a prior model of segmentations using the scaled-likelihood method. The prior model is based on a tree-structured belief network. Both the neural network and belief network were trained on a set of training images, and then the combined system was used to make predictions on a set of test images. We show that the combined neural network/belief network classifier gives improved prediction accuracy on 9 out of the 11 classes.

    Research areas

  • directed graphs, image classification, image segmentation, neural nets, prediction theory, trees (mathematics), belief networks, class labels, local predictions, scaled-likelihood method, training images, Artificial neural networks, Computer science, Fuses, Hidden Markov models, Image segmentation, Neural networks, Pattern classification, Pixel, Predictive models, System testing

ID: 21957842