Local figure-ground cues are valid for natural images
Figureground 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 figureground assignment in V2 as early as 1025 ms after response onset, providing strong support for the role of local bottomup 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 figureground relation by human observers, we quantified the extent to which figural regions locally tend to be smaller, more convex, and lie below ground regions. Our results suggest that these Gestalt cues are ecologically valid, and we quantify their relative power. We have also developed a simple bottomup computational model of figureground assignment that takes image contours as input. Using parameters fit to natural image statistics, the model is capable of matching human-level performance when scene context limited.
Text ReferenceCharless C. Fowlkes, David R. Martin, and Jitendra Malik. Local figure-ground cues are valid for natural images. Journal of Vision, 7(8):1–9, 2007. URL: http://journalofvision.org/7/8/2/.
author = "Fowlkes, Charless C. and Martin, David R. and Malik, Jitendra",
title = "Local figure-ground cues are valid for natural images",
journal = "Journal of Vision",
volume = "7",
number = "8",
url = "http://journalofvision.org/7/8/2/",
year = "2007",
pages = "1--9",
tag = "ecological_statistics"