Spatial Graphical Models for Image Matching and Object Recognition

Abstract

In this project we have had two partial successes. First is an efficient detection algorithm for objects in complex scenes, using very simple spatial arrangements to represent the objects, based on local features which are automatically identified in training. The simplicity of the arrangement allows us to use the Hough transform to very quickly find a small number of candidate locations for the objects. We have also proposed a parallel architecture for implementing this algorithm with interesting biological analogies. Second is an algorithm for isolated object recognition using decision trees to gradually explore the natural partial ordering of the space of spatial arrangements. The principles of this algorithm have also been successfully applied to the recognition of acoustic signals.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 18, 2000
Accession Number
ADA379291

Entities

People

  • Yali Amit

Organizations

  • University of Chicago

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Acoustic Signals
  • Algorithms
  • Character Recognition
  • Computations
  • Computer Vision
  • Computing System Architectures
  • Detection
  • Image Processing
  • Image Recognition
  • Information Science
  • Machine Learning
  • Markov Models
  • Neural Networks
  • Object Recognition
  • Recognition
  • Statistics
  • Training

Fields of Study

  • Computer science

Readers

  • Computer Vision.

Technology Areas

  • Space
  • Space - Space Objects