Segmenting Chromospheric Images with Markov Random Fields

  • Michael J. Turmon
  • Judit M. Pap
Conference paper


The solar chromosphere roughly consists of three types of region: plage, network, and background. Thresholding individual pixel intensities is typically used to identify these regions in solar images. We have incorporated spatial information by using a Bayesian setup with an image prior that prefers spatially coherent labelings; resulting segmentations are more physically reasonable. These priors are a first step in developing an appropriate model for chromospheric images.




Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media New York 1997

Authors and Affiliations

  • Michael J. Turmon
    • 1
  • Judit M. Pap
    • 2
  1. 1.Jet Propulsion LaboratoryPasadenaUSA
  2. 2.Department of AstronomyUCLALos AngelesUSA

Personalised recommendations