Cookies Policy

This site uses cookies. By continuing to browse the site you are agreeing to our use of cookies.

I accept this policy

Find out more here

Segmenting textured 3D surfaces using the space/frequency representation

No metrics data to plot.
The attempt to load metrics for this article has failed.
The attempt to plot a graph for these metrics has failed.
The full text of this article is not currently available.

Brill’s MyBook program is exclusively available on BrillOnline Books and Journals. Students and scholars affiliated with an institution that has purchased a Brill E-Book on the BrillOnline platform automatically have access to the MyBook option for the title(s) acquired by the Library. Brill MyBook is a print-on-demand paperback copy which is sold at a favorably uniform low price.

Access this article

+ Tax (if applicable)
Add to Favorites
You must be logged in to use this functionality

image of Spatial Vision
For more content, see Multisensory Research and Seeing and Perceiving.

—Segmenting 3D textured surfaces is critical for general image understanding. Unfortunately, current efforts of automatically understanding image texture are based on assumptions that make this goal impossible. Texture-segmentation research usually assumes that the textures are flat and viewed from the front, while shape-from-texture work assumes that the textures have already been segmented. This deadlock means that none of these algorithms will work reliably on images of 3D textured surfaces. An algorithm has been developed by the authors that can segment an image containing nonfrontally viewed, planar, periodic textures. The spectrogram (local power spectrum) is used to compute local surface normals from small regions of the image. This algorithm does not require unreliable image feature detection. Based on these surface normals, a 'frontalized' version of the local power spectrum is computed that shows what the region's power spectrum would look like if viewed from the front. If neighboring regions have similar frontalized power spectra, they are merged. The merge criterion is based on a description length formula. The segmentation is demonstrated on images with real textures. To the authors' knowledge, this is the first program that can segment 3D textured surfaces by explicitly accounting for 3D shape effects.

Affiliations: 1: The Robotics Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA


Full text loading...


Data & Media loading...

Article metrics loading...



Can't access your account?
  • Tools

  • Add to Favorites
  • Printable version
  • Email this page
  • Subscribe to ToC alert
  • Get permissions
  • Recommend to your library

    You must fill out fields marked with: *

    Librarian details
    Your details
    Why are you recommending this title?
    Select reason:
    Spatial Vision — Recommend this title to your library
  • Export citations
  • Key

  • Full access
  • Open Access
  • Partial/No accessInformation