Image Registration Improvement Based-on FFT Techniques with the Affine Transform Estimation

  • Wisetphanichkij, Sompong (Faculty of Engineering and Research Center for Communication and Information Technology, King Mongkut’s Institute of Technology Ladkrabang) ;
  • Pasomkusolsil, Sanchaiya (Faculty of Engineering and Research Center for Communication and Information Technology, King Mongkut’s Institute of Technology Ladkrabang) ;
  • Dejhan, Kobchai (Faculty of Engineering and Research Center for Communication and Information Technology, King Mongkut’s Institute of Technology Ladkrabang) ;
  • Cheevasuvit, Fusak (Faculty of Engineering and Research Center for Communication and Information Technology, King Mongkut’s Institute of Technology Ladkrabang) ;
  • Mitatha, Somsak (Faculty of Engineering and Research Center for Communication and Information Technology, King Mongkut’s Institute of Technology Ladkrabang) ;
  • Sra-Ium, Napat (Faculty of Engineering and Research Center for Communication and Information Technology, King Mongkut’s Institute of Technology Ladkrabang) ;
  • Vorrawat, Vinai (National Research Council of Thailand (NRCT)) ;
  • Pienvijarnpong, Chanchai (Geo-Informatics and Space Technology Development Agency (GISTDA))
  • Published : 2003.11.03

Abstract

New Image registration techniques are developed for determining geometric distortions between two images of the same scene. First, the properties of the Fourier transform of a two dimensional function under the affine transformation are given. As a result, techniques for the estimation of the coefficients of the distortion model using the spectral frequency information are developed. Image registration can be achieved by applying the fast Fourier transform (FFT) technique for cross correlation of misregistered imagery to determine spatial distances. The correlation results may be rather broad, making detection of the peak difficult, what can be suppressed by enhancing cross-correlation technique. Yield greatly improves the delectability and high precision of image misregistration.

Keywords