Digital Restoration of Painting Cracks

In this paper we develop a method for the restoration of cracks on a painting. First, we detect the local minima (they can be either cracks or painting brush strokes), by using a morphological highpass operator, called top-hat transformation. The crack filling procedure must be applied only on the cracks and not on these dark brush strokes, which are also detected. In order to separate these brush strokes from cracks, we use the Hue and Saturation information in the HSV or HSI color space. The separation is obtained by classification through the implementation of the MRBF neural network. Alternatively, a semi-automatic method is described for this separation. The primitive geometric shape-matching property of the morphological opening can be used to separate brush strokes, which have a specific shape. Finally, we propose two crack filling methods, one which is based on order statistics and another one using anisotropic diffusion. The results on painting crack restoration were very good.