• DocumentCode
    1440089
  • Title

    Local Affine Image Matching and Synthesis Based on Structural Patterns

  • Author

    Park, Heechan ; Martin, Graham R. ; Bhalerao, Abhir

  • Author_Institution
    Dept. of Comput. Sci., Univ. of Warwick, Coventry, UK
  • Volume
    19
  • Issue
    8
  • fYear
    2010
  • Firstpage
    1968
  • Lastpage
    1977
  • Abstract
    A general purpose block-to-block affine transformation estimator is described. The estimator is based on Fourier slice analysis and Fourier spectral alignment. It shows encouraging performance in terms of both speed and accuracy compared to existing methods. The key elements of its success are attributed to the ability to: 1) locate an arbitrary number of affine invariant points in the spectrum that latch onto significant structural features; 2) match the estimated invariant points with the target spectrum by the slicewise phase-correlation; and 3) use affine invariant points to directly compute all linear parameters of the full affine transform by spectral alignment. Experimental results using a wide range of textures are presented. Potential applications include affine invariant image segmentation, registration, affine symmetric image coding, and motion analysis.
  • Keywords
    Fourier analysis; image matching; Fourier slice analysis; Fourier spectral alignment; affine invariant image segmentation; affine invariant points; affine symmetric image coding; block-to-block affine transformation estimator; estimated invariant points; local affine image matching; motion analysis; slicewise phase-correlation; structural feature; structural patterns; target spectrum; Affine estimation; structural texture; Algorithms; Image Enhancement; Image Interpretation, Computer-Assisted; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Subtraction Technique;
  • fLanguage
    English
  • Journal_Title
    Image Processing, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1057-7149
  • Type

    jour

  • DOI
    10.1109/TIP.2010.2045704
  • Filename
    5430895