Bayesian Cross-Entropy Reconstruction of Complex Images

Abstract

Bajkova's generalized maximum entropy method (GMEM) for reconstruction of complex signals has been further generalized through the use of Kullback-Leibler cross entropy. This permits a priori information in the form of bias functions to be inserted into the algorithm, with resulting benefits to reconstruction quality. Also, the cross-entropy term is imbedded within an overall m.a.p. (maximum a posteriori probability) approach that includes a noise-rejection term. A further modification is transformation of the large, two-dimensional problem due to modest-sized 2-D images into a sequence of one- dimensional problems. Finally, the added operation of three-point median window filtration of each intermediary, one-dimensional output is shown to suppress edge-top overshoots while augmenting edge gradients. Applications to simulated complex images are shown.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 16, 1992
Accession Number
ADA261812

Entities

People

  • Anisa T. Bajkova
  • B. R. Frieden

Organizations

  • University of Arizona

Tags

DTIC Thesaurus Topics

  • Aircrafts
  • Airplanes
  • Algorithms
  • Artifacts
  • Astronomy
  • Bandwidth
  • Boundaries
  • Computer Simulations
  • Equations
  • Extrapolation
  • Frequency
  • Integrals
  • Noise
  • Pattern Recognition
  • Probability
  • Sequences
  • Two Dimensional

Readers

  • Computer Vision.
  • Finite Element Method (FEM) for solving Partial Differential Equations (PDEs)
  • Statistical inference.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks