The outlier process (picture processing)

Abstract

The authors discuss the problem of detecting outliers from a set of surface data. They start from the Bayes approach and the assumption that surfaces are piecewise smooth and corrupted by a combination of white Gaussian and salt and pepper noise. They show that such surfaces can be modelled by introducing an outlier process that is capable of 'throwing away' data. They make use of mean field techniques to finally obtain a deterministic network. The experimental results with real images support the model.<>