Unsupervised category modeling, recognition, and segmentation in images

Sinisa Todorovic, Narendra Ahuja

Research output: Contribution to journalArticlepeer-review


Suppose a set of arbitrary (unlabeled) images contains frequent occurrences of 2D objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: (1) unsupervised identification of photometric, geometric, and topological properties of multiscale regions comprising instances of the 2D category; (2) learning a region-based structural model of the category in terms of these properties; and (3) detection, recognition and segmentation of objects from the category in new images. To this end, each image is represented by a tree that captures a multiscale image segmentation. The trees are matched to extract the maximally matching subtrees across the set, which are taken as instances of the target category. The extracted subtrees are then fused into a tree-union that represents the canonical category model. Detection, recognition, and segmentation of objects from the learned category are achieved simultaneously by finding matches of the category model with the segmentation tree of a new image. Experimental validation on benchmark datasets demonstrates the robustness and high accuracy of the learned category models, when only a few training examples are used for learning without any human supervision.

Original languageEnglish (US)
Pages (from-to)2158-2174
Number of pages17
JournalIEEE transactions on pattern analysis and machine intelligence
Issue number12
StatePublished - 2008


  • Graph matching
  • Hierarchical object representation
  • Image segmentation tree
  • Object recognition
  • Tree union
  • Unsupervised learning

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'Unsupervised category modeling, recognition, and segmentation in images'. Together they form a unique fingerprint.

Cite this