Dynamical properties of image restoration and hyper-parameter estimation

Jun Ichi Inoue, Kazuyuki Tanaka

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

Dynamical properties of image restoration and hyper-parameter estimation are investigated by means of statistical mechanics. We introduce an exactly solvable model for image restoration and derive the differential equations with respect to macroscopic quantities. From these equations, we evaluate relaxation processes of the system to its equilibrium state in the sense of the Markov chain Monte Carlo (MCMC) method. Our statistical mechanical approach also enable one to investigate the hyper-parameter estimation by means of maximization of marginal likelihood using gradient decent, or the EM algorithm from dynamical point of view.

Original languageEnglish
Pages383-392
Number of pages10
Publication statusPublished - 2001 Dec 1

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Dynamical properties of image restoration and hyper-parameter estimation'. Together they form a unique fingerprint.

  • Cite this