• DocumentCode
    3320692
  • Title

    Animated depth employing image synthesis for 3D security X-ray imaging

  • Author

    Abusaeeda, O. ; Evans, J.P.O. ; Downes, D. ; Chan, J.W.

  • Author_Institution
    Imaging Sci. Group, Nottingham Trent Univ., Nottingham, UK
  • fYear
    2011
  • fDate
    14-17 Dec. 2011
  • Firstpage
    161
  • Lastpage
    166
  • Abstract
    We demonstrate the production of synthetic X-ray images by employing the scale invariant feature transform or SIFT in combination with epipolar morphing. The synthetic images are employed in a novel multiple view X-ray imaging technique to produce an animated or kinetic depth effect in a visual display. The synthetic views reduce the total number of X-ray detectors required during the image acquisition process. A quantitative analysis of the feature matching performance of the SIFT is presented along with a comparative study of the synthetic imagery. We show that the total number of matches produced by SIFT reduces as the angular separation between the generating views increases. This effect is accompanied by an increase in the total number of synthetic pixel errors. The trends observed are obtained from 15 different luggage items.
  • Keywords
    X-ray detection; X-ray imaging; computer animation; display instrumentation; image matching; security; stereo image processing; 3D security X-ray imaging; SIFT; X-ray detector; animated depth effect; animated depth employing image synthesis; epipolar morphing; feature matching; image acquisition process; invariant feature transform; kinetic depth effect; multiple view X-ray imaging technique; synthetic X-ray images; visual display; Clothing; Image recognition; Imaging; Pattern recognition; Security; Visualization; KDE; X-ray; image animation; kinetic depth; view synthesis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing and Information Technology (ISSPIT), 2011 IEEE International Symposium on
  • Conference_Location
    Bilbao
  • Print_ISBN
    978-1-4673-0752-9
  • Electronic_ISBN
    978-1-4673-0751-2
  • Type

    conf

  • DOI
    10.1109/ISSPIT.2011.6151553
  • Filename
    6151553