Statistical Image Restoration and Refinement,

Abstract

This document considers the problem of reconstructing an image from a noisy record. It describes methods due to Geman and Geman (1984) and Besag (1986) which use a Markov random field model for the true scene but assume that each pixel consists of a single colour. In order to improve the quality of the restoration at the boundary of regions of different colours the authors extend these methods to allow pixels to contain two regions of colour separated by a single straight line. An algorithm for performing the reconstruction is presented and illustrated by an example. Keywords: Split pixels, Restoration algorithms.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1986
Accession Number
ADA193736

Entities

People

  • Christopher Jennison
  • Michael Jubb

Organizations

  • University of Bath

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Bayesian Networks
  • Boundaries
  • Computations
  • Convergence
  • Data Science
  • Image Restoration
  • Information Science
  • Models
  • Probability
  • Random Variables
  • Schools
  • Statistical Analysis

Readers

  • Neural Network Machine Learning.
  • Statistical inference.
  • Vision Science/Vision Psychology/Cognitive Neuroscience.