Mean field and information theoretic algorithms for direct segmentation of tomographic images

Research output: Contribution to journalConference article

Abstract

We apply the weak membrane model with optimization by mean field annealing to the direct segmentation of tomographic images. We also introduce models based on the minimum description length principle that include penalties for measurement error, boundary length, regions, and means. Outliers are prevented by upper and lower bound constraints on pixel values. Several models are generalized to three-dimensional images. The superiority of our models to convolution back projection is demonstrated experimentally.

Original languageEnglish (US)
Pages (from-to)956-963
Number of pages8
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume1905
DOIs
StatePublished - Jul 29 1993
EventBiomedical Image Processing and Biomedical Visualization 1993 - San Jose, United States
Duration: Jan 31 1993Feb 5 1993

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Mean field and information theoretic algorithms for direct segmentation of tomographic images'. Together they form a unique fingerprint.

  • Cite this