Self-organization in vision: Stochastic clustering for image segmentation, perceptual grouping, and image database organization

Yoram Gdalyahu*, Daphna Weinshall, Michael Werman

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

143 Scopus citations


We present a stochastic clustering algorithm which uses pairwise similarity of elements and show how it can be used to address various problems in computer vision, including the low-level image segmentation, mid-level perceptual grouping, and high-level image database organization. The clustering problem is viewed as a graph partitioning problem, where nodes represent data elements and the weights of the edges represent pairwise similarities. We generate samples of cuts in this graph, by using Karger's contraction algorithm, and compute an "average" cut which provides the basis for our solution to the clustering problem. The stochastic nature of our method makes it robust against noise, including accidental edges and small spurious clusters. The complexity of our algorithm is very low: O(|E| log 2 N) for N objects, |E| similarity relations, and a fixed accuracy level. In addition, and without additional computational cost, our algorithm provides a hierarchy of nested partitions. We demonstrate the superiority of our method for image segmentation on a few synthetic and real images, both B&W and color. Our other examples include the concatenation of edges in a cluttered scene (perceptual grouping) and the organization of an image database for the purpose of multiview 3D object recognition.

Original languageAmerican English
Pages (from-to)1053-1074
Number of pages22
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number10
StatePublished - Oct 2001


  • Clustering
  • Image retrieval
  • Perceptual grouping
  • Segmentation


Dive into the research topics of 'Self-organization in vision: Stochastic clustering for image segmentation, perceptual grouping, and image database organization'. Together they form a unique fingerprint.

Cite this