• DocumentCode
    1043218
  • Title

    N-folded symmetries by complex moments in Gabor space and their application to unsupervised texture segmentation

  • Author

    Bigün, Josef ; Du Buf, J. M Hans

  • Author_Institution
    Signal Process. Lab., Swiss Federal Inst. of Technol., Lausanne, Switzerland
  • Volume
    16
  • Issue
    1
  • fYear
    1994
  • fDate
    1/1/1994 12:00:00 AM
  • Firstpage
    80
  • Lastpage
    87
  • Abstract
    Complex moments of the Gabor power spectrum yield estimates of the N-folded symmetry of the local image content at different frequency scales, that is, they allow to detect linear, rectangular, hexagonal/triangular, and so on, structures with very fine to very coarse resolutions. Results from experiments on the unsupervised segmentation of real textures indicate their importance for image processing applications. Real geometric moments computed in Gabor space also provide for very powerful texture features, but lack the clear geometrical interpretation of complex moments
  • Keywords
    image segmentation; numerical analysis; spectral analysis; Gabor power spectrum; Gabor space; N-folded symmetries; complex moments; frequency scales; hexagonal/triangular structures; linear structures; local image content; real geometric moments; rectangular structures; resolution; unsupervised texture segmentation; Anisotropic filters; Anisotropic magnetoresistance; Frequency estimation; Image processing; Image segmentation; Laboratories; Machine intelligence; Shape; Signal processing; Yield estimation;
  • fLanguage
    English
  • Journal_Title
    Pattern Analysis and Machine Intelligence, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0162-8828
  • Type

    jour

  • DOI
    10.1109/34.273714
  • Filename
    273714