Segmentation by grouping junctions

Hiroshi Ishikawa, Davi Geiger

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

102 Citations (Scopus)

Abstract

We propose a method for segmenting gray-value images. By segmentation, we mean a map from the set of pixels to a small set of levels such that each connected component of the set of pixels with the same level forms a relatively large and 'meaningful' region. The method finds a set of levels with associated gray values by first finding junctions in the image and then seeking a minimum set of threshold values that preserves the junctions. Then if finds a segmentation map that maps each pixel to the level with the closest gray value to the pixel data, within a smoothness constraint. For a convex smoothing penalty, we show the global optimal solution for an energy function that fits the data can be obtained in a polynomial time, by a novel use of the maximum-flow algorithm. Our approach is in contrast to a view in computer vision where segmentation is driven by intensity gradient, usually not yielding closed boundaries.

Original languageEnglish
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Comp Soc
Pages125-131
Number of pages7
Publication statusPublished - 1998
Externally publishedYes
EventProceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Santa Barbara, CA, USA
Duration: 1998 Jun 231998 Jun 25

Other

OtherProceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
CitySanta Barbara, CA, USA
Period98/6/2398/6/25

Fingerprint

Pixels
Computer vision
Polynomials

ASJC Scopus subject areas

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

Cite this

Ishikawa, H., & Geiger, D. (1998). Segmentation by grouping junctions. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 125-131). IEEE Comp Soc.

Segmentation by grouping junctions. / Ishikawa, Hiroshi; Geiger, Davi.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Comp Soc, 1998. p. 125-131.

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

Ishikawa, H & Geiger, D 1998, Segmentation by grouping junctions. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Comp Soc, pp. 125-131, Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Santa Barbara, CA, USA, 98/6/23.
Ishikawa H, Geiger D. Segmentation by grouping junctions. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Comp Soc. 1998. p. 125-131
Ishikawa, Hiroshi ; Geiger, Davi. / Segmentation by grouping junctions. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Comp Soc, 1998. pp. 125-131
@inproceedings{e279e2c89e65452bb6739d97be4cbc22,
title = "Segmentation by grouping junctions",
abstract = "We propose a method for segmenting gray-value images. By segmentation, we mean a map from the set of pixels to a small set of levels such that each connected component of the set of pixels with the same level forms a relatively large and 'meaningful' region. The method finds a set of levels with associated gray values by first finding junctions in the image and then seeking a minimum set of threshold values that preserves the junctions. Then if finds a segmentation map that maps each pixel to the level with the closest gray value to the pixel data, within a smoothness constraint. For a convex smoothing penalty, we show the global optimal solution for an energy function that fits the data can be obtained in a polynomial time, by a novel use of the maximum-flow algorithm. Our approach is in contrast to a view in computer vision where segmentation is driven by intensity gradient, usually not yielding closed boundaries.",
author = "Hiroshi Ishikawa and Davi Geiger",
year = "1998",
language = "English",
pages = "125--131",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Comp Soc",

}

TY - GEN

T1 - Segmentation by grouping junctions

AU - Ishikawa, Hiroshi

AU - Geiger, Davi

PY - 1998

Y1 - 1998

N2 - We propose a method for segmenting gray-value images. By segmentation, we mean a map from the set of pixels to a small set of levels such that each connected component of the set of pixels with the same level forms a relatively large and 'meaningful' region. The method finds a set of levels with associated gray values by first finding junctions in the image and then seeking a minimum set of threshold values that preserves the junctions. Then if finds a segmentation map that maps each pixel to the level with the closest gray value to the pixel data, within a smoothness constraint. For a convex smoothing penalty, we show the global optimal solution for an energy function that fits the data can be obtained in a polynomial time, by a novel use of the maximum-flow algorithm. Our approach is in contrast to a view in computer vision where segmentation is driven by intensity gradient, usually not yielding closed boundaries.

AB - We propose a method for segmenting gray-value images. By segmentation, we mean a map from the set of pixels to a small set of levels such that each connected component of the set of pixels with the same level forms a relatively large and 'meaningful' region. The method finds a set of levels with associated gray values by first finding junctions in the image and then seeking a minimum set of threshold values that preserves the junctions. Then if finds a segmentation map that maps each pixel to the level with the closest gray value to the pixel data, within a smoothness constraint. For a convex smoothing penalty, we show the global optimal solution for an energy function that fits the data can be obtained in a polynomial time, by a novel use of the maximum-flow algorithm. Our approach is in contrast to a view in computer vision where segmentation is driven by intensity gradient, usually not yielding closed boundaries.

UR - http://www.scopus.com/inward/record.url?scp=0032302953&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032302953&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0032302953

SP - 125

EP - 131

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

PB - IEEE Comp Soc

ER -