• DocumentCode
    3107257
  • Title

    Second Order Scattering Descriptors Predict fMRI Activity Due to Visual Textures

  • Author

    Eickenberg, Michael ; Senoussi, Mehdi ; Pedregosa, Fabian ; Gramfort, Alexandre ; Thirion, Bertrand

  • Author_Institution
    Parietal Team, INRIA Saclay-Ile-de-France, Saclay, France
  • fYear
    2013
  • fDate
    22-24 June 2013
  • Firstpage
    5
  • Lastpage
    8
  • Abstract
    Second layer scattering descriptors are known to provide good classification performance on natural quasi-stationary processes such as visual textures due to their sensitivity to higher order moments and continuity with respect to small deformations. In a functional Magnetic Resonance Imaging (fMRI) experiment we present visual textures to subjects and evaluate the predictive power of these descriptors with respect to the predictive power of simple contour energy - the first scattering layer. We are able to conclude not only that invariant second layer scattering coefficients better encode voxel activity, but also that well predicted voxels need not necessarily lie in known retinotopic regions.
  • Keywords
    biomedical MRI; image classification; image texture; classification performance; deformation; fMRI activity; functional magnetic resonance imaging; higher order moments; invariant second layer scattering coefficients; natural quasistationary processes; retinotopic regions; second order scattering descriptors; simple contour energy; visual textures; voxel activity; Brain modeling; Performance gain; Scattering; Sensitivity; Visualization; Wavelet transforms; encoding; fMRI; retinotopy; scattering;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition in Neuroimaging (PRNI), 2013 International Workshop on
  • Conference_Location
    Philadelphia, PA
  • Type

    conf

  • DOI
    10.1109/PRNI.2013.11
  • Filename
    6603543