Title :
Image restoration using a multilayer perceptron with a multilevel sigmoidal function
Author :
Sivakumar, K. ; Desai, U.B.
Author_Institution :
Dept. of Electr. & Comput. Eng., Johns Hopkins Univ., Baltimore, MD, USA
Abstract :
The problem of restoring a blurred and noisy image having many gray levels, without any knowledge of the blurring function and the statistics of the additive noise is considered. A multilevel sigmoidal function is used as the node linearity. Restoration is achieved by exploiting the generalization capabilities of the multilayer perceptron network. To overcome the burden of training time a segmentation scheme is suggested. Simulation results are also provided
Keywords :
feedforward neural nets; image reconstruction; image segmentation; additive noise; blurred image; blurring function; gray levels; image restoration; multilayer perceptron; multilevel sigmoidal function; node linearity; noisy image; segmentation scheme; Additive noise; Artificial neural networks; Hopfield neural networks; Image restoration; Image segmentation; Knowledge engineering; Multilayer perceptrons; Neurons; Statistics; Wiener filter;
Conference_Titel :
Circuits and Systems, 1992. ISCAS '92. Proceedings., 1992 IEEE International Symposium on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-0593-0
DOI :
10.1109/ISCAS.1992.230640
