Image processing for virtual restoration of artworks

摘要

As tools for artwork restoration, image-processing techniques serve two purposes. They can be used as a guide to the actual restoration of the artwork (computer-guided restoration). Or, they can produce a digitally restored version of the work, which itself is valuable, although the restoration is only virtual and cannot be reproduced on the real piece of work (virtual restoration). We present two applications of digital image processing for restoring artworks. The first belongs to the class of computer-guided restoration techniques, and the second represents an example of virtual artwork restoration. The first example refers to cleaning dirty paintings. More specifically, we describe a technique that, by relying on cleaning a small patch of the painting, can foresee the final result when the same cleaning methodology is applied to the whole piece of work. Restorers can use it by applying a set of different cleaning methodologies to very small patches of the painting. They can then use the virtual cleaning software to determine which cleaning procedure is likely to give the best result, thus using digital image processing as a tool to guide the actual restoration of the artwork. In our second example, we present a system for removing cracks from old paintings and frescos. In many cases, cracks severely deteriorate the aspect of paintings both because of their number and their heaviness. Thus, a system capable of removing them is of great interest, even if the removal is only virtual.