Segmenting Chromospheric Images with Markov Random Fields [chapter]

Michael J. Turmon, Judit M. Pap
1997 Statistical Challenges in Modern Astronomy II  
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.
doi:10.1007/978-1-4612-1968-2_31 fatcat:z2mp35g6cfed3i4pebju2so2im