Vision, Modeling, and Visualization (2020) J. Krüger, M. Niessner, and J. Stückler (Eds.) Segmenting Computer-Tomographic Scans of Ancient Clay Artefacts for Visual Analysis of Cuneiform Inscriptions T. Rolff 1 , M. Rautenhaus 2 S. Olbrich 2 and S. Frintrop 1 1 Department of Informatics, Universität Hamburg, Germany 2 Regional Computing Center, Universität Hamburg, Germany Abstract We address the automatic segmentation of computer tomographic scans of ancient clay tablets with cuneiform inscriptions enclosed inside a clay envelope. Such separation of parts of similar material properties in the scan enables domain scientists to virtually investigate the historically valuable artefacts by means of 3D visualization without physical destruction. We investigate two segmentation methods, the Priority-Flood algorithm and the Compact Watershed algorithm, the latter being modified by employing a distance metric that takes the ellipsoidal shape of the artefacts into account. Additionally, we propose a novel pre- segmentation method that suppresses the intensity values of the distance transform at contact points between clay envelope and tablet. We apply all methods to volumetric scans of a replicated clay tablet and analyze their performance under varying noise distributions. Evaluation by comparison to a manually segmented ground truth shows best results for the novel suppression- based approach. CCS Concepts • Human-centered computing → Scientific visualization; • Computing methodologies → Image processing; Volumetric mod- els; 1 Introduction In Kültepe, Turkey, approximately 22500 archaeological clay tablets mainly dating back to the nineteenth century BC have been discovered, with more tablets found at other sites [Mic08; Mic16]. Cuneiform inscriptions on these tablets range from legal docu- ments, including contracts, to private letters. They hence provide valuable insight into the customs and rites at the time of their cre- ation. As shown in Fig. 1, many of these tablets are still sealed within a protective envelope which is most likely manufactured from the same material [TC12]. The tablets were handcrafted, and a variety of different shapes in various conditions has been discov- ered. While some tablets are completely sealed in their envelopes, for others the envelope has been lost or has been accidentally shat- tered. Both the clay tablets and the envelopes feature inscriptions and illustrations. Therefore, both are of historical value and it is no option to destroy the envelope to gain access to the tablet content. A viable alternative solution is to perform computer tomographic (CT) scans of the discovered artefacts and to analyze the inscrip- tions using interactive 3D visualization. This raises the need for a robust segmentation algorithm capable of separating the clay tablet from its envelope. In this study, we address the challenge of per- forming such segmentation on volumetric data that was acquired using a CT scanner. Figure 1: 3D visualization of the partly cut protective clay envelope (red) and the enclosed clay tablet (blue) of the artefact available for our work, segmented using our proposed method. Both parts of the artefact, envelope and tablet, feature inscriptions that domain scientists are interested in analyzing. Best viewed in color. © 2020 The Author(s) Eurographics Proceedings © 2020 The Eurographics Association.