Information

  • Publication Type: Conference Paper
  • Workgroup(s)/Project(s):
  • Date: January 2007
  • ISBN: 978-80-86943-01-5
  • Series: WSCG’2007 Full Papers Proceedings
  • Publisher: University of West Bohemia
  • Organization: WSCG
  • Note: Full Paper
  • Location: Plzen, Czech Republic
  • Lecturer: Erald Vucini
  • Address: University of West Bohemia, Univerzitni 8, Box 314, CZ 306 14 Plzen, Czech Republic
  • Editor: Vaclav Skala
  • Booktitle: 15th WSCG 2007
  • Conference date: 29. January 2007 – 1. February 2007
  • Pages: 57 – 64
  • Keywords: Dimensionality Reduction, Face Recognition, Image Synthesis, Illumination Restoration

Abstract

This paper proposes a novel pipeline to develop a Face Recognition System robust to illumination variation. We consider the case when only one single image per person is available during the training phase. In order to utilize the superiority of Linear Discriminant Analysis (LDA) over Principal Component Analysis (PCA) in regard to variable illumination, a number of new images illuminated from different directions are synthesized from a single image by means of the Quotient Image. Furthermore, during the testing phase, an iterative algorithm is used for the restoration of frontal illumination of a face illuminated from any arbitrary angle. Experimental results on the YaleB database show that our approach can achieve a top recognition rate compared to existing methods and can be integrated into real time face recognition system.

Additional Files and Images

Weblinks

No further information available.

BibTeX

@inproceedings{vucini_erald-2007-FRI,
  title =      "Face Recognition under Varying Illumination",
  author =     "Erald Vucini and Muhittin G\"{o}kmen and Eduard Gr\"{o}ller",
  year =       "2007",
  abstract =   "This paper proposes a novel pipeline to develop a Face
               Recognition System robust to illumination variation. We
               consider the case when only one single image per person is
               available during the training phase. In order to utilize the
               superiority of Linear Discriminant Analysis (LDA) over
               Principal Component Analysis (PCA) in regard to variable
               illumination, a number of new images illuminated from
               different directions are synthesized from a single image by
               means of the Quotient Image. Furthermore, during the testing
               phase, an iterative algorithm is used for the restoration of
               frontal illumination of a face illuminated from any
               arbitrary angle. Experimental results on the YaleB database
               show that our approach can achieve a top recognition rate
               compared to existing methods and can be integrated into real
               time face recognition system.",
  month =      jan,
  isbn =       "978-80-86943-01-5",
  series =     "WSCG’2007 Full Papers Proceedings",
  publisher =  "University of West Bohemia",
  organization = "WSCG",
  note =       "Full Paper",
  location =   "Plzen, Czech Republic",
  address =    "University of West Bohemia, Univerzitni 8, Box 314, CZ 306
               14 Plzen, Czech Republic",
  editor =     "Vaclav Skala",
  booktitle =  "15th WSCG 2007",
  pages =      "57--64",
  keywords =   "Dimensionality Reduction, Face Recognition, Image Synthesis,
               Illumination Restoration",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2007/vucini_erald-2007-FRI/",
}