Skip to main content
Fig. 2 | Heritage Science

Fig. 2

From: Unveiling the invisible: mathematical methods for restoring and interpreting illuminated manuscripts

Fig. 2

First step in the detection of the damaged regions. This detection is based on the Chan-Vese segmentation described in “Chan-Vese segmentation” section. The user clicks on the damaged region to select training pixels (in blue) which serve as initialisation of the Chan-Vese model (1). The segmentation algorithm is run and the training region \(D_1\) inside the damaged area is segmented. The result is superimposed on the given image and coloured in yellow for better visualisation

Back to article page