An automated methodology for assessing the damage on Byzantine icons

Abstract

Byzantine art is overwhelmed by a multitude of icons that portray sacred faces. However, a large number of icons of historical value are either partially or totally damaged and thus in need of undergoing conservation. The detection and assessment of damage in cultural heritage artifacts comprise an integral part of the conservation process. In this paper, a method that can be used for assessing the damage on faces appearing in Byzantine icons is presented. The main approach involves the estimation of the residuals obtained after the coding and reconstruction of face image regions using trained Principal Component Analysis texture models. The extracted residuals can be used as the basis for obtaining information about the amount of damage and the positions of the damaged regions. Due to the specific nature of Byzantine icons several variations of the basic approach are tested through a quantitative experimental evaluation so that the methods most suited to the specific application domain are identified. As part of the experimental evaluation, holistic as well as patch-decomposition techniques have been utilized in order to catch the global and local information of the images, respectively. According to the results it is possible to detect and localize with reasonable accuracy the damaged areas of faces appearing in Byzantine icons