Shape Distances for Binary Image Segmentation

Frank R. Schmidt, Lena Gorelick, Ismail Ben Ayed, Yuri Boykov, Thomas Brox

Perspectives in Shape Analysis, Springer, page 137--154 - Oct 2016

Download the publication: 2.1 MB

Share the publication:

Shape distances are an important measure to guide the task of shape classification. In this chapter we show that the right choice of shape similarity is also important for the task of image segmentation, even at the absence of any shape prior. To this end, we will study three different shape distances and explore how well they can be used in a trust region framework. In particular, we explore which distance can be easily incorporated into trust region optimization and how well these distances work for theoretical and practical examples.

Images and movies

BibTex references

@InCollection\{SGBBB16a,
  author       = "Schmidt, Frank R. and Gorelick, Lena and Ben Ayed, Ismail and Boykov, Yuri and Brox, Thomas",
  title        = "Shape Distances for Binary Image Segmentation",
  booktitle    = "Perspectives in Shape Analysis",
  series       = "Mathematics and Visualization",
  pages        = "137--154",
  month        = "Oct",
  year         = "2016",
  editor       = "M. Breu{\ss}, A. Bruckstein, P. Maragos, S. Wuhrer",
  publisher    = "Springer",
  url          = "http://frank-r-schmidt.de/Publications/2016/SGBBB16a"
}