Statistical Filtering of Raster Map Images Using a Context Tree Model

We propose a statistical filter using a context tree modeling. The idea of context tree is to perform selective context expansion including only those pixel combinations that really appear in the image. This makes it possible to use much larger spatial neighborhood. The proposed context tree filtering is evaluated for a set of indexed-color raster map images corrupted with generated impulsive and content-dependent noise. The objective evaluation shows improvement of 15% for content-dependent noise and up to 30% for impulsive noise comparing to the closest competitor. Visual comparisons show that the spatial structures are preserved better than by vector median, morphological and peer group averaging filter.