ML Anthology

Self Inducing Relational Distance and Its Application to Image Segmentation

Jianbo Shi, Jitendra Malik
ECCV 1998 pp. 528-543
doi:10.1007/BFB0055688 /eccv/1998/shi1998eccv-self/

Abstract

We propose a new feature distance which is derived from an optimal relational graph matching criterion. Instead of defining an arbitrary similarity measure for grouping, we will use the criterion of reducing instability in the relational graph to induce a similarity measure. This similarity measure not only improves the stability of the matching, but more importantly, also captures the relative importance of relational similarity in the feature space for the purpose of grouping. We will call this similarity measure the self-induced relational distance. We demonstrate the distance measure on a brightness-texture feature space and apply it to the segmentation of complex natural images .

PDF ECCV Semantic Scholar

Cite

Text

Shi and Malik. "Self Inducing Relational Distance and Its Application to Image Segmentation." European Conference on Computer Vision, 1998. doi:10.1007/BFB0055688

Markdown

[Shi and Malik. "Self Inducing Relational Distance and Its Application to Image Segmentation." European Conference on Computer Vision, 1998.](https://mlanthology.org/eccv/1998/shi1998eccv-self/) doi:10.1007/BFB0055688

BibTeX

@inproceedings{shi1998eccv-self,
  title     = {{Self Inducing Relational Distance and Its Application to Image Segmentation}},
  author    = {Shi, Jianbo and Malik, Jitendra},
  booktitle = {European Conference on Computer Vision},
  year      = {1998},
  pages     = {528-543},
  doi       = {10.1007/BFB0055688},
  url       = {https://mlanthology.org/eccv/1998/shi1998eccv-self/}
}