On the Form of a Likelihood Ratio for Two-Dimensional Random Fields.

Abstract

It is shown that the likelihood ratio in detecting a stochastic signal in white Gaussian noise, when both the signal and the noise are two-dimensional random fields, does not have the simple exponential form of the one-dimensional case unless the signal is deterministic. This was conjectured by E. Wong were a recursive formula was derived for the likelihood ratio. Two auxiliary results of independent interest on conditional expectations are also shown.

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1975
Accession Number
ADA019533

Entities

People

  • Stamatis Cambanis

Organizations

  • University of North Carolina at Chapel Hill

Tags

DTIC Thesaurus Topics

  • Gaussian Noise
  • Geometry
  • Noise
  • Two Dimensional

Readers

  • Statistical inference.