May 2008
Volume 8, Issue 6
Free
Vision Sciences Society Annual Meeting Abstract  |   May 2008
A view-point invariant texture descriptor
Author Affiliations
  • Cornelia Fermuller
    University of Maryland
  • Yong Xu
    South China University of Technology
  • Hui Ji
    National University of Singapore
Journal of Vision May 2008, Vol.8, 354. doi:10.1167/8.6.354
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Cornelia Fermuller, Yong Xu, Hui Ji; A view-point invariant texture descriptor. Journal of Vision 2008;8(6):354. doi: 10.1167/8.6.354.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

A new texture descriptor based on fractal geometry, called the multi fractal spectrum (MFS) is introduced. The key quantity in the study of fractal geometry is the fractal dimension, which is a measure of how an object changes over scale. Consider the intensity of an image as a 3D surface and slice it at regular intervals at the dimension of height. For each interval we obtain a point set, for which we compute the fractal dimension. The vector composed of the fractal dimensions of all point sets is called the MFS of intensity. Replacing the intensity with other quantities, such as the density function, or the output of various filters (e.g. Laplacian, Gradient filters), different MFS descriptors are obtained. The MFS is shown mathematically to be invariant under any smooth mapping (bi-Lipschitz maps), which includes view-point changes and non-rigid deformations of the surface as well as local affine illumination changes. Computational experiments on unstructured textures, such as landscapes and shelves in a supermarket, demonstrate the robustness of the MFS to environmental changes. On standard data sets the MFS performs comparable to the top texture descriptors in the task of classification. However, in contrast to other descriptors, it has extremely low dimension and can be computed very efficiently and robustly. Psychophysical demonstrate that humans can differentiate black and white textures on the basis of the fractal dimension.

Fermuller, C. Xu, Y. Ji, H. (2008). A view-point invariant texture descriptor [Abstract]. Journal of Vision, 8(6):354, 354a, http://journalofvision.org/8/6/354/, doi:10.1167/8.6.354. [CrossRef]
Footnotes
 NSF, National Nature Science Foundation of China, China Scholarship Council.
×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×