Figure-ground organization refers to the visual perception that a contour
separating two regions belongs to one of the regions. Recent studies have
found neural correlates of figure-ground assignment in V2 as early as 10-25
msec after response onset, suggesting a singificant for the role of local,
bottom-up processing. How much information about figure-ground assignment is
available from locally computed cues? Using a large collection of natural
images in which neighboring regions were assigned a figure-ground relation by
human observers, we quantified the extent to which figural regions tend to be
smaller, more convex and lie below ground regions. Our results suggest that
these Gestalt cues are ecologically valid. We have also developed a bottom-up
computational model of figure-ground assignment, using parameters fit to
natural image statistics, that is capable of matching human-level performance
when scene context limited.
- Figure-ground assignments for a large set of natural images
- C. Fowlkes, D. Martin, J. Malik. "Local Figure/Ground Cues are Valid for Natural Images"
Journal of Vision, 7(8):2, 1-9. [pdf]
- X. Ren, C. Fowlkes, J. Malik. "Figure/Ground Assignment in Natural Images",
ECCV, Graz, Austria, (May 2006).
- X. Ren, C. Fowlkes, J. Malik. "Familiar configuration enables
figure/ground assignment in natural scenes", VSS, Sarasota,
FL, (May 2005). [Journal of
Vision, 5(8) p.344] [pdf]
- C. Fowlkes, D. Martin, J. Malik. "On Measuring the Ecological Validity of Local Figure-Ground Cues",
, Paris, (Sept. 2003).