Title :
A Bayesian approach to 2D non minimum phase AR identification
Author :
Jacovitti, Giovanni ; Neri, Alessandro
Author_Institution :
Info-Com. Dept., Rome Univ., Italy
Abstract :
The authors deal with estimation of autoregressive (AR) noncausal models of bidimensional signals. The problem of factorizing an image into an excitation with a given marginal p.d.f. and a IIR filter is formulated in a Bayesian conceptual framework. The proposed solution is an iterative procedure for the minimization of the a posteriori risk associated to a given cost function. The procedure implies the inversion of a Toeplitz-block-Toeplitz covariance matrix and the iterated solution of a set of normal equations associated with a nonlinear estimation stage.<>
Keywords :
Bayes methods; computerised picture processing; digital filters; iterative methods; parameter estimation; 2D nonminimum phase autoregressive identification; Bayesian conceptual framework; IIR filter; Toeplitz-block-Toeplitz covariance matrix; a posteriori risk; bidimensional signals; cost function; image processing; iterative procedure; marginal PDF; matrix inversion; noncausal models; nonlinear estimation stage; normal equations; Bayesian methods; Cost function; Covariance matrix; Deconvolution; Entropy; Equations; Finite impulse response filter; Higher order statistics; Phase estimation; Signal processing;
Conference_Titel :
Spectrum Estimation and Modeling, 1990., Fifth ASSP Workshop on
Conference_Location :
Rochester, NY, USA
DOI :
10.1109/SPECT.1990.205550
