Patch-cuts: A graph-based image segmentation method using patch features and spatial relations

Gerd Brunner, Deepak R. Chittajallu, Uday Kurkure, Ioannis A. Kakadiaris

Research output: Contribution to conferencePaper

5 Citations (Scopus)

Abstract

In this paper, we present a graph-based image segmentation method (patch-cuts) that incorporates features and spatial relations obtained from image patches. In the first step, patch-cuts extracts a set of patches that can assume arbitrary shape and size. Patches are determined by a combination of intensity quantization and morphological operations and render the proposed method robust against noise. Upon patch extraction, a set of intensity, texture and shape features are computed for each patch. These features are integrated and minimized simultaneously in a tunable energy function. Patch-cuts explores the benefit of information theory-based measures such as the Kullback-Leibler and the Jensen-Shannon divergence in its energy terms. In our experiments, we applied patchcuts to general images as well as to non-contrast Computed Tomography heart scans.

Original languageEnglish (US)
DOIs
StatePublished - Jan 1 2010
Event2010 21st British Machine Vision Conference, BMVC 2010 - Aberystwyth, United Kingdom
Duration: Aug 31 2010Sep 3 2010

Conference

Conference2010 21st British Machine Vision Conference, BMVC 2010
CountryUnited Kingdom
CityAberystwyth
Period8/31/109/3/10

Fingerprint

Information theory
Image segmentation
Tomography
Textures
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Brunner, G., Chittajallu, D. R., Kurkure, U., & Kakadiaris, I. A. (2010). Patch-cuts: A graph-based image segmentation method using patch features and spatial relations. Paper presented at 2010 21st British Machine Vision Conference, BMVC 2010, Aberystwyth, United Kingdom. https://doi.org/10.5244/C.24.29
Brunner, Gerd ; Chittajallu, Deepak R. ; Kurkure, Uday ; Kakadiaris, Ioannis A. / Patch-cuts : A graph-based image segmentation method using patch features and spatial relations. Paper presented at 2010 21st British Machine Vision Conference, BMVC 2010, Aberystwyth, United Kingdom.
@conference{d21089733f004bd7ba7752ffd280be23,
title = "Patch-cuts: A graph-based image segmentation method using patch features and spatial relations",
abstract = "In this paper, we present a graph-based image segmentation method (patch-cuts) that incorporates features and spatial relations obtained from image patches. In the first step, patch-cuts extracts a set of patches that can assume arbitrary shape and size. Patches are determined by a combination of intensity quantization and morphological operations and render the proposed method robust against noise. Upon patch extraction, a set of intensity, texture and shape features are computed for each patch. These features are integrated and minimized simultaneously in a tunable energy function. Patch-cuts explores the benefit of information theory-based measures such as the Kullback-Leibler and the Jensen-Shannon divergence in its energy terms. In our experiments, we applied patchcuts to general images as well as to non-contrast Computed Tomography heart scans.",
author = "Gerd Brunner and Chittajallu, {Deepak R.} and Uday Kurkure and Kakadiaris, {Ioannis A.}",
year = "2010",
month = "1",
day = "1",
doi = "10.5244/C.24.29",
language = "English (US)",
note = "2010 21st British Machine Vision Conference, BMVC 2010 ; Conference date: 31-08-2010 Through 03-09-2010",

}

Brunner, G, Chittajallu, DR, Kurkure, U & Kakadiaris, IA 2010, 'Patch-cuts: A graph-based image segmentation method using patch features and spatial relations' Paper presented at 2010 21st British Machine Vision Conference, BMVC 2010, Aberystwyth, United Kingdom, 8/31/10 - 9/3/10, . https://doi.org/10.5244/C.24.29

Patch-cuts : A graph-based image segmentation method using patch features and spatial relations. / Brunner, Gerd; Chittajallu, Deepak R.; Kurkure, Uday; Kakadiaris, Ioannis A.

2010. Paper presented at 2010 21st British Machine Vision Conference, BMVC 2010, Aberystwyth, United Kingdom.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Patch-cuts

T2 - A graph-based image segmentation method using patch features and spatial relations

AU - Brunner, Gerd

AU - Chittajallu, Deepak R.

AU - Kurkure, Uday

AU - Kakadiaris, Ioannis A.

PY - 2010/1/1

Y1 - 2010/1/1

N2 - In this paper, we present a graph-based image segmentation method (patch-cuts) that incorporates features and spatial relations obtained from image patches. In the first step, patch-cuts extracts a set of patches that can assume arbitrary shape and size. Patches are determined by a combination of intensity quantization and morphological operations and render the proposed method robust against noise. Upon patch extraction, a set of intensity, texture and shape features are computed for each patch. These features are integrated and minimized simultaneously in a tunable energy function. Patch-cuts explores the benefit of information theory-based measures such as the Kullback-Leibler and the Jensen-Shannon divergence in its energy terms. In our experiments, we applied patchcuts to general images as well as to non-contrast Computed Tomography heart scans.

AB - In this paper, we present a graph-based image segmentation method (patch-cuts) that incorporates features and spatial relations obtained from image patches. In the first step, patch-cuts extracts a set of patches that can assume arbitrary shape and size. Patches are determined by a combination of intensity quantization and morphological operations and render the proposed method robust against noise. Upon patch extraction, a set of intensity, texture and shape features are computed for each patch. These features are integrated and minimized simultaneously in a tunable energy function. Patch-cuts explores the benefit of information theory-based measures such as the Kullback-Leibler and the Jensen-Shannon divergence in its energy terms. In our experiments, we applied patchcuts to general images as well as to non-contrast Computed Tomography heart scans.

UR - http://www.scopus.com/inward/record.url?scp=84898426854&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898426854&partnerID=8YFLogxK

U2 - 10.5244/C.24.29

DO - 10.5244/C.24.29

M3 - Paper

AN - SCOPUS:84898426854

ER -

Brunner G, Chittajallu DR, Kurkure U, Kakadiaris IA. Patch-cuts: A graph-based image segmentation method using patch features and spatial relations. 2010. Paper presented at 2010 21st British Machine Vision Conference, BMVC 2010, Aberystwyth, United Kingdom. https://doi.org/10.5244/C.24.29