Title :
Image restoration using neural networks
Author :
De Figueiredo, M. Teles ; Leitão, JoséM N.
Author_Institution :
Dept. de Engenharia Electrotecnica e de Computadores, Inst. Superior Tecnico, Lisboa, Portugal
Abstract :
Two neural algorithms for image restoration are proposed. The image is considered degraded by linear blur and additive white Gaussian noise. Maximum a posteriori estimation and regularization theory applied to this problem lead to the same high dimension optimization problem. The developed schemes, one having a sequential updating schedule and the other being fully parallel, implement iterative minimization algorithms which are proved to converge. The robustness of these algorithms with respect to finite numerical precision is studied. Examples with real images are presented
Keywords :
image reconstruction; neural nets; additive white Gaussian noise; finite numerical precision; image restoration; iterative minimization algorithms; linear blur; maximum a posteriori estimation; neural networks; optimization problem; parallel algorithms; regularization theory; sequential updating schedule; Additive white noise; Degradation; Image converters; Image restoration; Iterative algorithms; Maximum a posteriori estimation; Minimization methods; Neural networks; Noise robustness; Scheduling algorithm;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0532-9
DOI :
10.1109/ICASSP.1992.226033
