• Media type: Doctoral Thesis; E-Book; Electronic Thesis; Text
  • Title: A Robust Face Recognition Algorithm for Real-World Applications
  • Contributor: Ekenel, Hazim Kemal [Author]
  • imprint: KIT-Bibliothek, Karlsruhe, 2009-01-01
  • Language: English
  • DOI: https://doi.org/10.5445/IR/1000014999
  • Keywords: DATA processing & computer science ; robust face recognition ; local appearance modeling ; discrete cosine transform
  • Origination:
  • Footnote: Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
  • Description: The proposed face recognition algorithm utilizes representation of local facial regions with the DCT. The local representation provides robustness against appearance variations in local regions caused by partial face occlusion or facial expression, whereas utilizing the frequency information provides robustness against changes in illumination. The algorithm also bypasses the facial feature localization step and formulates face alignment as an optimization problem in the classification stage.
  • Access State: Open Access