GCH 2014 - Eurographics Workshop on Graphics and Cultural Heritage

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/7755

Browse

Browsing GCH 2014 - Eurographics Workshop on Graphics and Cultural Heritage by Subject "Applications"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Extending Philological Research with Methods of 3D Computer Graphics Applied to Analysis of Cultural Heritage
    (The Eurographics Association, 2014) Fisseler, Denis; Weichert, Frank; Müller, Gerfrid G. W.; Cammarosano, Michele; Reinhard Klein and Pedro Santos
    Philological research on ancient cuneiform texts with the goal of analyzing and reconstructing manuscripts from a large quantity of available unsorted tablet fragments is a time consuming task. As the number of tablet fragments and the number of signs on the fragments both exceed values which can be handled by means of conventional manual research methods in a reasonable amount of time, the use of computer aided research methods is an obvious choice. In this paper, we present a novel unified approach for integrating methods of computer graphics into the process of analyzing and joining cuneiform tablet fragments. We will cover a selection of essential research scenarios and identify aspects where those methods can be applied to enhance and extend traditional philological research processes or even help to access formerly unavailable layers of information. This is achieved by integrating methods for visualization, interactive 3D script feature extraction, script analysis, virtual fragment joining and intuitive measurement and annotation tools in our fast and easy to use software framework CuneiformAnalyser, designed for large data sets. Unlike other approaches, our solution integrates for the first time methods to support every aspect of the manuscript analysis and reconstruction process in a single system.
  • Thumbnail Image
    Item
    A TaLISMAN: Automatic Text and LIne Segmentation of historical MANuscripts
    (The Eurographics Association, 2014) Pintus, Ruggero; Yang, Ying; Gobbetti, Enrico; Rushmeier, Holly; Reinhard Klein and Pedro Santos
    Historical and artistic handwritten books are valuable cultural heritage (CH) items, as they provide information about tangible and intangible cultural aspects from the past. Massive digitization projects have made these kind of data available to a world-wide population, and pose real challenges for automatic processing. In this scenario, document layout analysis plays a significant role, being a fundamental step of any document image understanding system. In this paper, we present a completely automatic algorithm to perform a robust text segmentation of old handwritten manuscripts on a per-book basis, and we show how to exploit this outcome to find two layout elements, i.e., text blocks and text lines. Our proposed technique have been evaluated on a large and heterogeneous corpus content, and our experimental results demonstrate that this approach is efficient and reliable, even when applied to very noisy and damaged books.