Logo des Repositoriums

Auflistung nach Schlagwort "Image Processing"

1 - 3 von 3
  • Konferenzbeitrag
    Integrating the Technologies of Image Processing and Virtual Reality for the Digital Preservation of Disappeared Archaeological Sites
    (INFORMATIK 2024, 2024) Al-Ameen, Zohair; Mahmood, Basim; Al-Sarraf, Abdullah; Alchalabi, Oday
    Tangible historical and cultural assets refer to physical artifacts that can be touched and intergenerationally transferred. This kind of asset is considered the past that the next generations should memorize. One of the issues that archaeologists frequently face is the methods used in digitally restoring disappeared archaeological assets. This is due to their low quality, noisy texture, or uncolored images. On the other hand, the advent of new technologies such as digital image processing (DIP) and virtual reality (VR) makes it palatable to digitalize and sustain tangible historical assets. These technologies are recognized as efficient tools insofar as they can contribute to preserving the heritage of civilizations. Hence, this study suggests an approach that integrates DIP and VR techniques to restore historical assets that have disappeared from low-quality images. The findings show that the proposed methodology is successful in restoring archaeological sites or objects, as demonstrated by the results obtained.
  • Textdokument
    Object Detection and Classification in Digital Surface Models of the Lausitz Region in Germany
    (INFORMATIK 2021, 2021) Kalloch, Benjamin; Tontchev, Toni; Hlawitschka, Mario
  • Konferenzbeitrag
    Shallow CNNs for the Reliable Detection of Facial Marks
    (BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group, 2018) Zeinstra, Chris; Haasnoot, Erwin
    Facial marks are local irregularities of skin texture. Their type and/or spatial pattern can be used as a (soft) biometric modality in several applications. A key requirement for a biometric system that utilises facial marks is their reliable detection. Detection methods typically use a blob detector followed by heuristic post processing steps to reduce the number of false positives. In this paper, we consider shallow Convolutional Neural Networks (CNNs) for facial mark detection. The choice of this network type seems natural as it learns multiple (non) blob detectors; shallow refers to the fact that we only consider CNNs up to three layers.We show that (a) these CNNs successfully address the false positive problem, (b) remove the need for post processing steps, and (c) outperform a classic blob detector, approaches taken in previous studies and some other non CNN type classifiers in terms of EER and FMR at TMR=0.95.