Estimate boundaries in a binary image. This function may be used directly with list objects with the format of par2obs output.
BayesBDbinary(obs, inimean, nrun, nburn, J, ordering, mask, slice, outputAll)The noisy observation which is a list with the following required elements:
intensity: observed intensity at each pixel.
theta.obs, r.obs: the location of the pixel at which the intensity is observed, using polar coordinates with respect to a reference point.
center: the reference point for polar coords (theta.obs, r.obs).
a constant to specify the initial mean functions in the Bayesian estimation.
the number of MCMC samples to keep for estimation.
the number of initial MCMC samples to discard.
truncation number of the Gaussian process kernel. The number of eigenfunctions is \(2J + 1\).
Indicates which Bernoulli distribution has larger success probability: "I", the Bernoulli distribution inside the boundary; "O", the Bernoulli distribution outside the boundary; "N", no ordering information is available.
Logical vector (same length as obs$intensity) to indicate region of interest. Should this data point be included in the analysis?
boolean where TRUE means that slice sampling will be used to sample Fourier basis function coefficients and FALSE means that Metropolis-Hastings will be used instead.
boolean controlling the amount of output produced, see value below.
If outputAll is FALSE,
Posterior mean estimate of image boundary at theta values.
A grid of 200 values on \([0,2\pi]\) at which to retrun the estimated boundary.
The lower and upper bounds of a \(95\%\) uniform credible band for the image boundary.
posterior samples of \(\pi_1\) and \(\pi_2\).
posterior samples of Fourier basis function coefficients.
Li, M. and Ghosal, S.(2015) "Bayesian Detection of Image Boundaries." arXiv 1508.05847.