Figure-ground classification based on spectral properties of boundary image patches

Sudarshan Ramenahalli, Stefan Mihalas, Ernst Niebur

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Image understanding requires segregation of the visual scene into perceptual objects. Due to the projection of the three-dimensional world on two-dimensional sensor surfaces, objects closer to the observer occlude those which are more distant. At any given occlusion border, it is important to decide which side is the foreground (figure) and which is the background, a decision which is influenced both by global and local image contents. In this report, we focus on local cues. We randomly select small image patches located on figure-ground borders in complex natural scenes. Spectral anisotropy features are extracted from the patches and used to train a non-linear Support Vector Machine. Using data from two large image databases (LabelMe and BSDS300), the classifier achieves an accuracy near 70% per local patch on the task of deciding which side of an occlusion is the foreground. Although in many cases global influences are important for figure-ground segregation, we suggest that the low computational cost of local computation can make it a useful strategy for figure-ground segregation.

Original languageEnglish (US)
Title of host publication2012 46th Annual Conference on Information Sciences and Systems, CISS 2012
DOIs
StatePublished - Nov 12 2012
Event2012 46th Annual Conference on Information Sciences and Systems, CISS 2012 - Princeton, NJ, United States
Duration: Mar 21 2012Mar 23 2012

Publication series

Name2012 46th Annual Conference on Information Sciences and Systems, CISS 2012

Other

Other2012 46th Annual Conference on Information Sciences and Systems, CISS 2012
CountryUnited States
CityPrinceton, NJ
Period3/21/123/23/12

ASJC Scopus subject areas

  • Information Systems

Fingerprint Dive into the research topics of 'Figure-ground classification based on spectral properties of boundary image patches'. Together they form a unique fingerprint.

  • Cite this

    Ramenahalli, S., Mihalas, S., & Niebur, E. (2012). Figure-ground classification based on spectral properties of boundary image patches. In 2012 46th Annual Conference on Information Sciences and Systems, CISS 2012 [6310943] (2012 46th Annual Conference on Information Sciences and Systems, CISS 2012). https://doi.org/10.1109/CISS.2012.6310943