Statistical Object Recognition

Abstract

To be practical, recognition systems must deal with uncertainty. Positions of image features in scenes vary. Features sometimes fail to appear because of unfavorable illumination. In this work, methods of statistical inference are combined with empirical models of uncertainty in order to evaluate and refine hypotheses about the occurrence of a known object in a scene. Probabilistic models are used to characterize image features and their correspondences. A statistical approach is taken for the acquisition of object models from observations in images: Mean Edge Images are used to capture object features that are reasonably stable with respect to variations in illumination.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1993
Accession Number
ADA270887

Entities

People

  • William M. Wells Iii

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Energy and Power Technologies
  • Sensors

DTIC Thesaurus Topics

  • Acquisition
  • Artificial Intelligence
  • Computer Graphics
  • Computer Science
  • Computer Vision
  • Detectors
  • Electrical Engineering
  • Image Processing
  • Information Science
  • Neural Networks
  • Object Recognition
  • Pattern Recognition
  • Probabilistic Models
  • Probability
  • Statistical Inference
  • Three Dimensional
  • Two Dimensional

Readers

  • Computational Modeling and Simulation
  • Image Processing and Computer Vision.
  • Theoretical Analysis.

Technology Areas

  • AI & ML