Title :
Unsupervised deconvolution of satellite images
Author :
Khoumri, Mustapha ; Blanc-Feraud, Laure ; Zerubia, Josiane
Author_Institution :
INRIA, Sophia Antipolis, France
Abstract :
This paper focuses on hyperparameter estimation of a variational model for image deconvolution. Using the generalized maximum likelihood (GML) estimator, the estimation problem is reduced to the ML estimation in the case of perfectly observed data. A method based on stochastic gradient is then developed for the estimation of both linear and nonlinear hyperparameters
Keywords :
deconvolution; geophysical signal processing; image processing; maximum likelihood estimation; remote sensing; variational techniques; GML estimator; ML estimation; estimation problem; generalized maximum likelihood estimator; hyperparameter estimation; image deconvolution; linear hyperparameters; nonlinear hyperparameters; perfectly observed data; satellite images; stochastic gradient; unsupervised deconvolution; variational model; Additive noise; Convolution; Deconvolution; Degradation; Image restoration; Maximum likelihood estimation; Satellites; Stochastic processes; Stochastic resonance; Stochastic systems;
Conference_Titel :
Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on
Conference_Location :
Chicago, IL
Print_ISBN :
0-8186-8821-1
DOI :
10.1109/ICIP.1998.723322
