Title :
Deconvolutionwith gaussian blur parameter and hyperparameters estimation
Author :
Orieux, François ; Giovannelli, Jean-François ; Rodet, Thomas
Author_Institution :
Lab. des Signaux et Syst., Univ. Paris-Sud 11, Gif-sur-Yvette, France
Abstract :
This paper proposes a Bayesian approach for unsupervised image deconvolution when the parameter of the gaussian PSF is unknown. The parameters of the regularization parameters are also unknown and jointly estimated with the other parameters. The solution is found by inferring on a global a posteriori law for unknown object and parameters. The estimate is chosen in the sense of the posterior mean, numerically calculated by means of a Monte-Carlo Markov chain algorithm. The computation is efficiently done in Fourier space and the practicability of the method is shown on simulated examples. Results show high-frequencies restoration in the estimated image with correct estimation of the hyperparameters and instrument parameters.
Keywords :
Bayes methods; Gaussian processes; Markov processes; Monte Carlo methods; deconvolution; image restoration; parameter estimation; Bayesian approach; Fourier space; Gaussian PSF parameter; Gaussian blur parameter; Monte-Carlo Markov chain algorithm; a posteriori law; deconvolution; high-frequency restoration; hyperparameter estimation; unsupervised image deconvolution; Bayesian methods; Computational modeling; Deconvolution; Image restoration; Instruments; Medical simulation; Optical imaging; Parameter estimation; Pixel; Shape; Image restoration; Monte-Carlo Markov chain; full-bayesian approach; myopic deconvolution; unsupervised deconvolution;
Conference_Titel :
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on
Conference_Location :
Dallas, TX
Print_ISBN :
978-1-4244-4295-9
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2010.5495444