TY - CHAP A1 - Arlt, Tobias A1 - Lindow, Norbert A1 - Baum, Daniel A1 - Hilger, Andre A1 - Mahnke, Ingo A1 - Hege, Hans-Christian A1 - Lepper, Verena A1 - Siopi, Tzulia A1 - Mahnke, Heinz.Eberhard T1 - Virtual Access to Hidden Texts – Study of Ancient Papyri T2 - Eighth Joint BER II and BESSY II User Meeting, Dec 7-9, 2016, Berlin, Germany N2 - When physical unfolding/unrolling of papyri is not possible or too dangerous for preserving the precious object, tomographic approaches may be the ap- propriate alternative. Requirements are the resolution and the contrast to distinguish writing and substrate. The steps to be performed are the following: (1) Select the object of interest (archaeological arguments, cultural back- ground of the object, etc.). (2) Find the proper physical procedure, especially with respect to contrast, take the tomographic data, e.g. by absorption x-ray tomography. (3) Apply mathematical unfolding transformations to the tomographic data, in order to obtain a 2d-planar reconstruction of text. Y1 - 2016 ER - TY - CHAP A1 - Klenert, Nicolas A1 - Schwoerer, Finn A1 - Hajarolasvadi, Noushin A1 - Bournez, Siloé A1 - Arlt, Tobias A1 - Mahnke, Heinz-Eberhard A1 - Lepper, Verena A1 - Baum, Daniel T1 - Improving the Identification of Layers in 3D Images of Ancient Papyrus using Artificial Neural Networks T2 - 2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), Tucson, AZ, USA N2 - The process of digitally unfolding ancient documents, such as folded papyrus packages, from 3D image data aims to be a non-invasive means to make previously hidden writing visible without risking to damage the precious documents. One of the main tasks necessary to digitally unfold a document is the geometric reconstruction of the writing substrate, which is a prerequisite for its subsequent unfolding. All current reconstruction methods require the existence of an interspace between different layers of the document to ensure a correct topology. Layers that appear merged together in the 3D image often result in wrong connections between layers and thus also in a wrong topology of the reconstructed geometry, which hinders the successful unfolding. Here, we propose to use a neural network to facilitate the discrimination of the layers. Using papyrus documents as an example of a particularly difficult writing material, we show that this significantly reduces the number of wrong connections and improves the overall identification of the layers. This in turn enables fully automatic digital unfolding of large areas of highly complex papyrus packages. Utilizing explainable AI (XAI) further allows us to explore the results of the applied neural network. Y1 - 2025 U6 - https://doi.org/10.1109/WACVW65960.2025.00143 SP - 1204 EP - 1212 ER -