Spatially coherent clustering using graph cuts

R. Zabih, V. Kolmogorov, in:, IEEE, 2004, pp. 437–444.

Download
No fulltext has been uploaded. References only!

Conference Paper | Published
Author
Abstract
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.
Publishing Year
Date Published
2004-06-01
Volume
2
Page
437 - 444
Conference
CVPR: Computer Vision and Pattern Recognition
IST-REx-ID

Cite this

Zabih R, Kolmogorov V. Spatially coherent clustering using graph cuts. In: Vol 2. IEEE; 2004:437-444. doi:10.1109/CVPR.2004.1315196
Zabih, R., & Kolmogorov, V. (2004). Spatially coherent clustering using graph cuts (Vol. 2, pp. 437–444). Presented at the CVPR: Computer Vision and Pattern Recognition, IEEE. https://doi.org/10.1109/CVPR.2004.1315196
Zabih, Ramin, and Vladimir Kolmogorov. “Spatially Coherent Clustering Using Graph Cuts,” 2:437–44. IEEE, 2004. https://doi.org/10.1109/CVPR.2004.1315196.
R. Zabih and V. Kolmogorov, “Spatially coherent clustering using graph cuts,” presented at the CVPR: Computer Vision and Pattern Recognition, 2004, vol. 2, pp. 437–444.
Zabih R, Kolmogorov V. 2004. Spatially coherent clustering using graph cuts. CVPR: Computer Vision and Pattern Recognition vol. 2. 437–444.
Zabih, Ramin, and Vladimir Kolmogorov. Spatially Coherent Clustering Using Graph Cuts. Vol. 2, IEEE, 2004, pp. 437–44, doi:10.1109/CVPR.2004.1315196.

Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar