September 2005
Volume 5, Issue 8
Free
Vision Sciences Society Annual Meeting Abstract  |   September 2005
Familiar configuration enables figure/ground assignment in natural scenes
Author Affiliations
  • Xiaofeng Ren
    University of California at Berkeley
  • Charless Fowlkes
    University of California at Berkeley
  • Jitendra Malik
    University of California at Berkeley
Journal of Vision September 2005, Vol.5, 344. doi:https://doi.org/10.1167/5.8.344
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Xiaofeng Ren, Charless Fowlkes, Jitendra Malik; Familiar configuration enables figure/ground assignment in natural scenes. Journal of Vision 2005;5(8):344. https://doi.org/10.1167/5.8.344.

      Download citation file:


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

      ×
  • Supplements
Abstract

Figure/ground organization is a step of perceptual organization that assigns a contour to one of the two abutting regions. Peterson et al showed that familiar configurations of contours, such as outlines of recognizable objects, provide a powerful cue that can dominate traditional f/g cues such as symmetry. In this work we: (1) provide an operationalization of “familiar configuration” in terms of prototypical local shapes, without requiring global object recognition; (2) show that a classifier based on this cue works well on images of natural scenes.

A dataset of 200 natural images was hand segmented into disjoint regions by human subjects. Subjects then provided a f/g label for each contour associated with a pair of abutting segments [Fowlkes, Martin & Malik ECVP03]. Our goal is to correctly predict these f/g labels from image measurements.

We use “shape context” to represent local shape configuration at each point. Shape context [Belongie, Malik & Puzicha ICCV01] is a shape descriptor which summarizes local arrangement of edges, relative to the center point, in a log-polar fashion. In order to work with grayscale images, we use a variant of shape context, geometric blur [Berg & Malik CVPR01], aligned to local tangent direction. We cluster a large set of these descriptors to construct a small list of prototypical shape configurations, or “shapemes” (analogous to phonemes). Shapemes capture important local structures such as convexity and parallelism.

For each point along a contour, we measure the similarity of its local shape descriptor to each shapeme. These measurements are combined using a logistic regression classifier to predict the f/g label. By averaging the classifier outputs over all points on each contour, we obtain an error rate of 30% (chance is 50%). This compares favorably to the traditional f/g cues used in [Fowlkes et al 03]. Enforcing consistency constraints at junctions reduces the error rate further to 22%, making it a promising model of figure/ground organization.

Ren, X. Fowlkes, C. Malik, J. (2005). Familiar configuration enables figure/ground assignment in natural scenes [Abstract]. Journal of Vision, 5(8):344, 344a, http://journalofvision.org/5/8/344/, doi:10.1167/5.8.344. [CrossRef]
×
×

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.

×