Spectral Embedding and Min Cut for Image Segmentation

@inproceedings{Estrada2004SpectralEA,
  title={Spectral Embedding and Min Cut for Image Segmentation},
  author={Francisco J. Estrada and Allan D. Jepson and Chakra Chennubhotla},
  booktitle={BMVC},
  year={2004}
}
Recently it has been shown that min-cut algorithms can provide perceptually salient image segments when they are given appropriate proposals for source and sink regions. Here we explore the use of random walks and associated spectral embedding techniques for the automatic generation of suitable proposal regions. To do this, we first derive a mathematical connection between spectral embedding and anisotropic image smoothing kernels. We then use properties of the spectral embedding and the… CONTINUE READING
Highly Cited
This paper has 37 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.

Similar Papers

Loading similar papers…