Detection and removal of cracks on digitized paintings

Image processing techniques used to detect and remove crack can be employed to inspection and/or diagnosis. Besides it can be useful for, improve her perceptiveness (legibility) of the digital images. In particularly this is true for the digital images used for didactic or multimedia applications. An integrated methodology for the detection and removal of cracks on digitized paintings is presented in this paper. Here we focus the attention on the possibility of classification and virtual cancellation of cracks on digitized old paintings. In this way, a "virtual" restoration is performed. It can provide clues to art historians, museum curators and the general public on how the painting would look like in its initial state, i.e., without the cracks. Furthermore, it can be used as a nondestructive tool for the planning of the actual restoration. A methodology to identify and to restore the present cracks on digital images is introduced in this paper. The technique consists of the following stages: (a) Detection of the cracks; (b) Separation of the brush strokes, which have been misidentified as cracks; (c) Implementation of the crack filling procedure.