Profil Henrike Stephani

Schwerpunkte/Kompetenzen

  • 2-D Bildverarbeitung
  • Machine Learning/Deep Learning
  • Künstliche Intelligenz
  • Hyperspektrale Bildverarbeitung

 

Publikationen

Highlightpublikationen

  • Nieradzik, L.; Stephani, H.; Sieburg-Rockel, J.; Helmling, S.; Olbrich, A. and Keuper, J.:
    Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestry.
    In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2024).
  • Nieradzik, L.; Sieburg-Rockel, J.; Helmling, S.; Keuper, J.; Weibel, T.; Olbrich, A. and Stephani, H.:
    Automating Wood Species Detection and Classification in Microscopic Images of Fibrous Materials with Deep Learning.
    arXiv preprint arXiv:2307.09588. (2023)
  • Stephani, H.; Weibel, T.; Rösch, R.; Moghiseh, A.:
    Challenges and approaches when realizing online surface inspection systems with deep learning algorithms.
    Discover Data: Volume 1, Article number: 3 (2023)
  • Müller, O.; Fend, C.; Moghiseh, A.; Schladitz, K.; Stephani, H.; Weibel, T.:
    Deep learning for image based shelve inventories.
    10th International Symposium on Signal, Image, Video and Communications, ISIVC 2020: Saint-Etienne, France, 7–9 April 2021. Piscataway, NJ: IEEE, 2021.
  • Lichti, M.; Cheng, X.; Stephani, H.; Bart, H.-J.:
    Online Detection of Ellipsoidal Bubbles by an Innovative Optical Approach. 
    Chemical Engineering and Technology Vol. 42 (2), pp.506-511, (2019)
  • Müller, O.; Moghiseh, A.; Stephani, H.; Rottmayer, N.; Huang, F.:
    Application of deep learning for crack segmentation on concrete surface.
    Forum Bildverarbeitung 2018: 29. und 30. November 2018, Karlsruhe
    KIT Scientific Publishing, (2018)
  • Stephani, H.; Weibel, T.; Moghiseh, A.:
    Modellbasiertes Lernen in der Oberflächeninspektion.
    Automatisierungstechnik: AT 65, Nr.6, S.406-415, (2017)

Sammlung der Publikationen von Henrike Stephani in der Fraunhofer-Publica