Object Recognition via Information-Theoretic Measures/Metrics

Abstract

Discrimination of friendly or hostile objects is investigated using information-theory measures/metric in an image which has been compromised by a number of factors. In aerial military images, objects with different orientation can be reasonably approximated by a single identification signature consisting of the average histogram of the object under rotations. Three different information-theoretic measures/metrics are studied as possible criteria to help classify the objects.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 2006
Accession Number
ADA472482

Entities

People

  • Alan R. Pinkus
  • Christian D. Schrider
  • Daniel W. Repperger
  • Julie A. Skipper

Organizations

  • Air Force Research Laboratory

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Computer Vision
  • Discrimination
  • Engineering
  • Histograms
  • Identification
  • Industrial Engineering
  • Information Operations
  • Information Theory
  • Military Research
  • Object Recognition
  • Orientation (Direction)
  • Recognition
  • Rotation

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Sensor Fusion and Tracking Systems.