Detection And Removal Of Cracks In Digitized Paintings

Several methods have been proposed for detection and removal of cracks in digitized paintings. Cracks deteriorate the quality of painting. A technique for the detection and removal of cracks in digitized image paintings that adapts and integrates a number of processing and analysis tools for digitized image painting is presented in this paper. The cracks are detected by thresholding the output of the morphological top-hat transform. After detecting cracks, a modified adaptive median filter (MAMF) is used to fill the cracks. The methodology performs very well on digitized paintings suffering from cracks.