GIScience integrated with computer vision for the examination of old engravings and drawings

Landscape reconstructions and deep maps are two major approaches in cultural heritage studies. In general, they require the use of historical visual sources such as maps, graphic artworks, photographs presenting areal scenes, from which one can extract spatial information. However, photographs, most accurate reliable source for scenery reconstruction, available only second half 19th century onward. Thus, earlier periods rely on old artworks. Nevertheless, accuracy inclusiveness artworks often questionable must be verified carefully.In this paper, we GIScience methods with computer-vision capabilities to interrogate engravings drawings well develop a new approach extracting information these scenic We have inspected four depictions Jerusalem Tiberias (Israel) created between 17th centuries. Using visibility analysis RANSAC algorithm identified locations artists when drew evaluated their final products. Finally, re-projected 3D map digitized features onto drawing canvases, thus embedding not originally drawn. These were then identified, enabling potential extraction may reflect.Video abstract is at: https://youtu.be/dmt74VKsfF8