Image Segmentation via Probabilistic Graph Matching

Ayelet Heimowitz, Yosi Keller

Research output: Contribution to journalArticlepeer-review

19 Scopus citations


This paper presents an unsupervised and semi-automatic image segmentation approach where we formulate the segmentation as an inference problem based on unary and pairwise assignment probabilities computed using low-level image cues. The inference is solved via a probabilistic graph matching scheme, which allows rigorous incorporation of low-level image cues and automatic tuning of parameters. The proposed scheme is experimentally shown to compare favorably with contemporary semi-supervised and unsupervised image segmentation schemes, when applied to contemporary state-of-the-art image sets.

Original languageEnglish
Article number7511662
Pages (from-to)4743-4752
Number of pages10
JournalIEEE Transactions on Image Processing
Issue number10
StatePublished - Oct 2016
Externally publishedYes


  • Image segmentation
  • inference algorithms
  • machine learning
  • semisupervised learning
  • statistical learning
  • unsupervised learning


Dive into the research topics of 'Image Segmentation via Probabilistic Graph Matching'. Together they form a unique fingerprint.

Cite this