Identification of drawing tools by classification of textural and boundary features of strokes
Pattern Recognition Letters
Stroke segmentation in infrared reflectograms
SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
Computer aided analysis of underdrawings in infrared reflectograms
VAST'03 Proceedings of the 4th International conference on Virtual Reality, Archaeology and Intelligent Cultural Heritage
Restoration of X-ray fluorescence images of hidden paintings
Signal Processing
Feature vector definition for a decision tree based craquelure identification in old paintings
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
| Hi-index | 0.00 |
A method for the elimination of cracks in infrared reflectograms is presented. Infrared reflectograms show the underdrawing 驴 the basic concept of the artist drawn on theground layer 驴 in ancient wood panel paintings. Caused by different mechanical behaviour of the panel and the covering ground layer during the aging of the painting, cracksappear. Cracks not only disturb the appearance of a painting, but are also a problem for segmenting the lines and strokes of the underdrawing. A method based on mathematical morphology, namely morphological reconstruction with viscosity, is used to eliminate the cracks while keeping as much detail as possible in the brush strokes. A priori information that the cracks are usually thinner than the brush strokes and have a preferred orientation is taken into account.