ML Anthology

Randomized Algorithm of Spectral Clustering and Image/video Segmentation Using a Minority of Pixels

Tomoya Sakai, Atsushi Imiya
ICCVW 2009 pp. 468-475
doi:10.1109/ICCVW.2009.5457665 /iccvw/2009/sakai2009iccvw-randomized/

Abstract

We propose a randomized algorithm of spectral clustering and apply it to appearance-based image/video segmentation. Spectral clustering is a kernel-based method of grouping data on separate nonlinear manifolds. However, its high computational expensive restricts the applications. Our algorithm exploits random projection and subsampling techniques for reducing dimensionality and cardinality of data. The computation time can be independent of data dimensionality in appearance-based methods, and is quasilinear with respect to the data cardinality. We demonstrate our spectral clustering algorithm in image and video shot segmentation.

ICCVW Semantic Scholar

Cite

Text

Sakai and Imiya. "Randomized Algorithm of Spectral Clustering and Image/video Segmentation Using a Minority of Pixels." IEEE/CVF International Conference on Computer Vision Workshops, 2009. doi:10.1109/ICCVW.2009.5457665

Markdown

[Sakai and Imiya. "Randomized Algorithm of Spectral Clustering and Image/video Segmentation Using a Minority of Pixels." IEEE/CVF International Conference on Computer Vision Workshops, 2009.](https://mlanthology.org/iccvw/2009/sakai2009iccvw-randomized/) doi:10.1109/ICCVW.2009.5457665

BibTeX

@inproceedings{sakai2009iccvw-randomized,
  title     = {{Randomized Algorithm of Spectral Clustering and Image/video Segmentation Using a Minority of Pixels}},
  author    = {Sakai, Tomoya and Imiya, Atsushi},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2009},
  pages     = {468-475},
  doi       = {10.1109/ICCVW.2009.5457665},
  url       = {https://mlanthology.org/iccvw/2009/sakai2009iccvw-randomized/}
}