Deutsch Intern
    Chair of Computer Science VI - Artificial Intelligence and Applied Computer Science

    Alexander Hartelt, M. Sc.

    University of Würzburg
    Chair of Artificial Intelligence
    and Knowledge Systems
    Am Hubland
    D-97074 Würzburg

     

    Room:  B014
    Phone: +49 931 / 31-84275


    alexander.hartelt@uni-wuerzburg.de

    About Me

    In May 2019, I received my master’s degree in computer science at the University of Würzburg. Since July 2019 I work at the chair of Artificial Intelligence and Knowledge Systems in the field of Computer Vision. My research focus is in particular on digitization of historical documents.

    Research Interests

    • Computer Vision

    • Document analysis

    • Layout detection/analysis

    • Optical character recognition (especially on handwritten documents)

    • Information extraction

    • Deep Learning based segmentation algorithms

    Projects

    The Corpus Monodicum project is dedicated to the research, transcription and edition of music-historically significant, editorially still unexplored collections. In the context of this project, the transcription tool Ommr4all was developed, which provides tools and algorithms in a web interface to perform a semi-automatic transcription of these.
    This is currently my main research focus.

    Furthermore, I am part of the internal project Segmentation of Old Prints, which is also dedicated to the research and application of algorithms for segmentation and transcription of historical prints. Various tools have been developed (e.g. pixel classifier, contour-based approaches, baseline approaches), which are used for transcribing documents.

    Teaching

    Since WS 20/21 Artificial Intelligence I (Exercise)
    Regularly Seminar "Current Trends in artficial Intelligence" (Supervision for topics)
    Regularly Software Practical Course (Supervisor for Topics)

    Publications

    • Lyrics Recognition and Syllable Assignment of Medieval Music Manuscripts. Wick, Christoph; Hartelt, Alexander; Puppe, Frank. In 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), bll 187–192. 2020.
    • {OMMR4all - ein semiautomatischer Online-Editor für mittelalterliche Musiknotationen}. Wick, Christoph; Hartelt, Alexander; Puppe, Frank. Zenodo, 2020.
    • Contour-Based Segmentation of Historical Printings. Fischer, Norbert; Gehrke, Alexander; Hartelt, Alexander; Krug, Markus; Puppe, Frank. In KI, Vol. 12325Lecture Notes in Computer Science, U. Schmid, F. Klügl, D. Wolter (reds.), bll 46–58. Springer, 2020.
    • OCR4all - An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings. Reul, Christian; Christ, Dennis; Hartelt, Alexander; Balbach, Nico; Wehner, Maximilian; Springmann, Uwe; Wick, Christoph; Grundig, Christine; Büttner, Andreas; Puppe, Frank. In ArXiv Preprints (submitted to MDPI - Applied Sciences). 2019.
    • Staff, Symbol and Melody Detection of Medieval Manuscripts Written in Square Notation Using Deep Fully Convolutional Networks. Wick, Christoph; Hartelt, Alexander; Puppe, Frank. In Applied Sciences, 9(13). 2019.