• DocumentCode
    3512506
  • Title

    An individual identification by using an angled facial data

  • Author

    Terada, K. ; Yonetani, Y. ; Ohashi, G. ; Yamaguchi, J.

  • Author_Institution
    Fac. of Eng., Tokushima Univ., Japan
  • Volume
    3
  • fYear
    1999
  • fDate
    1999
  • Firstpage
    1324
  • Abstract
    In this paper, the authors propose a method of identifying individuals using the angled facial image obtained from a CCD camera. The authors believe that they can obtain more effective data for identifying faces by setting the CCD camera at an angle to the faces concerned. When a CCD camera like this is set, they believe that effective information is able to be obtained from the large region, of one side of the face, the information of nose height which is one of three dimensional facial information and the cheek undulation which is part of the outline of their profiles. Before the identification of the face is carried out with the use of this angled image data, calibrations relative to the positions, the scales and the directions of the faces of the subjects at the time the data were obtained. The input data for identification is composed of the following; the edge image of the certain region around the right eye; the gray image of the certain region around the mouth; the shape of the nose; and the shape of the outline of the angled face. Experiments using the experimental system are performed to demonstrate the efficacy of this method and the experimental results are shown
  • Keywords
    CCD image sensors; calibration; edge detection; face recognition; identification; CCD camera; angled facial data; calibration; cheek undulation; edge image; gray image; individual identification; input data; nose height; noses shape; Calibration; Charge coupled devices; Charge-coupled image sensors; Face; Humans; Monitoring; Mouth; Nose; Security; Shape;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Industrial Electronics Society, 1999. IECON '99 Proceedings. The 25th Annual Conference of the IEEE
  • Conference_Location
    San Jose, CA
  • Print_ISBN
    0-7803-5735-3
  • Type

    conf

  • DOI
    10.1109/IECON.1999.819403
  • Filename
    819403