---
OA_type: closed access
_id: '3177'
abstract:
- lang: eng
  text: Feature space clustering is a popular approach to image segmentation, in which
    a feature vector of local properties (such as intensity, texture or motion) is
    computed at each pixel. The feature space is then clustered, and each pixel is
    labeled with the cluster that contains its feature vector. A major limitation
    of this approach is that feature space clusters generally lack spatial coherence
    (i.e., they do not correspond to a compact grouping of pixels). In this paper,
    we propose a segmentation algorithm that operates simultaneously in feature space
    and in image space. We define an energy function over both a set of clusters and
    a labeling of pixels with clusters. In our framework, a pixel is labeled with
    a single cluster (rather than, for example, a distribution over clusters). Our
    energy function penalizes clusters that are a poor fit to the data in feature
    space, and also penalizes clusters whose pixels lack spatial coherence. The energy
    function can be efficiently minimized using graph cuts. Our algorithm can incorporate
    both parametric and non-parametric clustering methods. It can be applied to many
    optimization-based clustering methods, including k-means and k-medians, and can
    handle models which are very close in feature space. Preliminary results are presented
    on segmenting real and synthetic images, using both parametric and non-parametric
    clustering.
article_processing_charge: No
author:
- first_name: Ramin
  full_name: Zabih, Ramin
  last_name: Zabih
- first_name: Vladimir
  full_name: Kolmogorov, Vladimir
  id: 3D50B0BA-F248-11E8-B48F-1D18A9856A87
  last_name: Kolmogorov
citation:
  ama: 'Zabih R, Kolmogorov V. Spatially coherent clustering using graph cuts. In:
    <i>Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision
    and Pattern Recognition, 2004</i>. Vol 2. IEEE; 2004:437-444. doi:<a href="https://doi.org/10.1109/CVPR.2004.1315196">10.1109/CVPR.2004.1315196</a>'
  apa: 'Zabih, R., &#38; Kolmogorov, V. (2004). Spatially coherent clustering using
    graph cuts. In <i>Proceedings of the 2004 IEEE Computer Society Conference on
    Computer Vision and Pattern Recognition, 2004</i> (Vol. 2, pp. 437–444). Washington,
    DC, United States: IEEE. <a href="https://doi.org/10.1109/CVPR.2004.1315196">https://doi.org/10.1109/CVPR.2004.1315196</a>'
  chicago: Zabih, Ramin, and Vladimir Kolmogorov. “Spatially Coherent Clustering Using
    Graph Cuts.” In <i>Proceedings of the 2004 IEEE Computer Society Conference on
    Computer Vision and Pattern Recognition, 2004</i>, 2:437–44. IEEE, 2004. <a href="https://doi.org/10.1109/CVPR.2004.1315196">https://doi.org/10.1109/CVPR.2004.1315196</a>.
  ieee: R. Zabih and V. Kolmogorov, “Spatially coherent clustering using graph cuts,”
    in <i>Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision
    and Pattern Recognition, 2004</i>, Washington, DC, United States, 2004, vol. 2,
    pp. 437–444.
  ista: 'Zabih R, Kolmogorov V. 2004. Spatially coherent clustering using graph cuts.
    Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and
    Pattern Recognition, 2004. CVPR: Computer Vision and Pattern Recognition vol.
    2, 437–444.'
  mla: Zabih, Ramin, and Vladimir Kolmogorov. “Spatially Coherent Clustering Using
    Graph Cuts.” <i>Proceedings of the 2004 IEEE Computer Society Conference on Computer
    Vision and Pattern Recognition, 2004</i>, vol. 2, IEEE, 2004, pp. 437–44, doi:<a
    href="https://doi.org/10.1109/CVPR.2004.1315196">10.1109/CVPR.2004.1315196</a>.
  short: R. Zabih, V. Kolmogorov, in:, Proceedings of the 2004 IEEE Computer Society
    Conference on Computer Vision and Pattern Recognition, 2004, IEEE, 2004, pp. 437–444.
conference:
  end_date: 2004-07-02
  location: Washington, DC, United States
  name: 'CVPR: Computer Vision and Pattern Recognition'
  start_date: 2004-06-27
date_created: 2018-12-11T12:01:50Z
date_published: 2004-06-01T00:00:00Z
date_updated: 2026-09-11T12:20:17Z
day: '01'
doi: 10.1109/CVPR.2004.1315196
extern: '1'
fulldoi: https://doi.org/10.1109/CVPR.2004.1315196
intvolume: '         2'
language:
- iso: eng
month: '06'
oa_version: None
page: 437 - 444
publication: Proceedings of the 2004 IEEE Computer Society Conference on Computer
  Vision and Pattern Recognition, 2004
publication_identifier:
  isbn:
  - '0769521584'
  issn:
  - 1063-6919
publication_status: published
publisher: IEEE
publist_id: '3506'
status: public
title: Spatially coherent clustering using graph cuts
type: conference
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 2
year: '2004'
...