Extracting Subimages of an Unknown Category from a Set of Images

Abstract

Suppose a set of images contains frequent occurrences of objects from an unknown category. This paper is aimed at simultaneously solving the following related problems "1" unsupervised identification of photometric, geometric, and topological "mutual containment" properties of multi-scale regions defining objects in the category; "2" learning a region-based structural model of the category in terms of these properties from a set of training images; and "3" segmentation and recognition 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 find the maximally matching subtrees across the set, the existence of which is itself viewed as evidence that a category is indeed present. The matched sub-trees are fused into a canonical tree, which represents the learned model of the category. Recognition of objects in a new image and image segmentation delineating all object parts are achieved simultaneously by finding matches of the model with subtrees of the new image. Experimental comparison with state-of-the-art methods shows that the proposed approach has similar recognition and superior localization performance while it uses fewer training examples.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2006
Accession Number
ADA480892

Entities

People

  • Narendra Ahuja
  • Sinisa Todorovic

Organizations

  • University of Illinois Urbana–Champaign

Tags

Communities of Interest

  • Air Platforms

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Boundaries
  • Computational Complexity
  • Computer Vision
  • Databases
  • Detection
  • Image Recognition
  • Image Segmentation
  • Information Science
  • Learning
  • Pattern Recognition
  • Precision
  • Recognition
  • Statistical Distributions
  • Training
  • Two Dimensional

Readers

  • Computer Vision.
  • Systems Analysis and Design