Title :
Double deconvolution using a neural network
Author_Institution :
Dept. of Math., Hong Kong Baptist Coll., Hong Kong
Abstract :
The restoration of a blurred digital image usually requires accurate knowledge of the blurring process which, however, may not always be available. This paper describes a double iterative scheme for the simultaneous identification of the blurring and its removal by making use of the neural network paradigm and assumption of physical constraints on the blurring process
Keywords :
image reconstruction; iterative methods; neural nets; blurred digital image restoration; blurring removal; double deconvolution; double iterative scheme; neural network; Deconvolution; Degradation; Educational institutions; Frequency estimation; Image restoration; Inverse problems; Mathematics; Neural networks; Optical filters; Optical noise;
Conference_Titel :
Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on
Print_ISBN :
0-7803-1865-X
DOI :
10.1109/SIPNN.1994.344824
