Skip to main content
Fig. 3 | Heritage Science

Fig. 3

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

Fig. 3

Second step in the detection of the damaged region. The k-means clustering algorithm is run on the whole image selection in terms of intensity-based image features, cf. “Image descriptors: feature extraction” and “A clustering algorithm with training” sections. The outputs of the binary segmentation algorithm shown in Fig. 2 are used as guidance for the clustering algorithm

Back to article page