Visual organization for figure/ground separation

Davi Geiger, Krishnan Kumaran, Laxmi Parida

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

Abstract

A common factor in all illusory contour figures is the perception of a surface occluding part of a background. In our previous work, we have shown we could diffuse a proper set of junction hypothesis (what is salient or background) to obtain a surface where their boundaries represented illusory contours. Amodal completions emerge at the overlapping surfaces. We address the problem of selecting the best image organization (set of hypothesis). We propose an optimization criteria based on a coherence measure between pairs of junctions (correlation between the diffusion of each pair). A statistical physics approach to select the best organization is applied. The experiments suggest that despite the large number of possible organizations our approach may take only a few steps (in organization space) to select the best one.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE
Pages155-160
Number of pages6
StatePublished - 1996
EventProceedings of the 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - San Francisco, CA, USA
Duration: Jun 18 1996Jun 20 1996

Other

OtherProceedings of the 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
CitySan Francisco, CA, USA
Period6/18/966/20/96

Fingerprint

Physics
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Geiger, D., Kumaran, K., & Parida, L. (1996). Visual organization for figure/ground separation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 155-160). IEEE.

Visual organization for figure/ground separation. / Geiger, Davi; Kumaran, Krishnan; Parida, Laxmi.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, 1996. p. 155-160.

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

Geiger, D, Kumaran, K & Parida, L 1996, Visual organization for figure/ground separation. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, pp. 155-160, Proceedings of the 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, 6/18/96.
Geiger D, Kumaran K, Parida L. Visual organization for figure/ground separation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE. 1996. p. 155-160
Geiger, Davi ; Kumaran, Krishnan ; Parida, Laxmi. / Visual organization for figure/ground separation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, 1996. pp. 155-160
@inproceedings{90f01f1a541a48b99fa1408758d9bdee,
title = "Visual organization for figure/ground separation",
abstract = "A common factor in all illusory contour figures is the perception of a surface occluding part of a background. In our previous work, we have shown we could diffuse a proper set of junction hypothesis (what is salient or background) to obtain a surface where their boundaries represented illusory contours. Amodal completions emerge at the overlapping surfaces. We address the problem of selecting the best image organization (set of hypothesis). We propose an optimization criteria based on a coherence measure between pairs of junctions (correlation between the diffusion of each pair). A statistical physics approach to select the best organization is applied. The experiments suggest that despite the large number of possible organizations our approach may take only a few steps (in organization space) to select the best one.",
author = "Davi Geiger and Krishnan Kumaran and Laxmi Parida",
year = "1996",
language = "English (US)",
pages = "155--160",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE",

}

TY - GEN

T1 - Visual organization for figure/ground separation

AU - Geiger, Davi

AU - Kumaran, Krishnan

AU - Parida, Laxmi

PY - 1996

Y1 - 1996

N2 - A common factor in all illusory contour figures is the perception of a surface occluding part of a background. In our previous work, we have shown we could diffuse a proper set of junction hypothesis (what is salient or background) to obtain a surface where their boundaries represented illusory contours. Amodal completions emerge at the overlapping surfaces. We address the problem of selecting the best image organization (set of hypothesis). We propose an optimization criteria based on a coherence measure between pairs of junctions (correlation between the diffusion of each pair). A statistical physics approach to select the best organization is applied. The experiments suggest that despite the large number of possible organizations our approach may take only a few steps (in organization space) to select the best one.

AB - A common factor in all illusory contour figures is the perception of a surface occluding part of a background. In our previous work, we have shown we could diffuse a proper set of junction hypothesis (what is salient or background) to obtain a surface where their boundaries represented illusory contours. Amodal completions emerge at the overlapping surfaces. We address the problem of selecting the best image organization (set of hypothesis). We propose an optimization criteria based on a coherence measure between pairs of junctions (correlation between the diffusion of each pair). A statistical physics approach to select the best organization is applied. The experiments suggest that despite the large number of possible organizations our approach may take only a few steps (in organization space) to select the best one.

UR - http://www.scopus.com/inward/record.url?scp=0029702953&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029702953&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029702953

SP - 155

EP - 160

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

PB - IEEE

ER -