Virtual restoration of cracks in digitized image of paintings

An integrated methodology for the detection and removal of cracks on digitized image is presented in this paper. Crack-like pattern detection have been a matter of high concern among researchers mostly for its useful contribution to a variety of applications. The results presented here regard the craquelure of old paintings, however, the same methodology can be used for a much wider set of application. Many images contain similar patterns: crack in protective coating for polymers and other surfaces; fatigue crack in MEMS/NEMS; crack in epoxies used for underfill and encapsulation microelectronics components; etc. In this paper the cracks are detected by thresholding the output of the morphological top-hat transform. Afterwards, the thin dark brush strokes which have been misidentified as cracks are removed using automatic procedure. Finally, crack filling using texture synthesis algorithms. The methodology has been shown to perform very well on digitized images suffering from cracks.