IMAGE-RESTORATION USING A MULTILAYER PERCEPTRON WITH A MULTILEVEL SIGMOIDAL FUNCTION
DSpace at IIT Bombay
View Archive InfoField | Value | |
Title |
IMAGE-RESTORATION USING A MULTILAYER PERCEPTRON WITH A MULTILEVEL SIGMOIDAL FUNCTION
|
|
Creator |
SIVAKUMAR, K
DESAI, UB |
|
Description |
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 nonlinearity, due to which the same number of nodes as in the case of a binary image is sufficient for an image with multiple gray levels. Restoration is achieved by exploiting the generalization capabilities of the multilayer perceptron network. For realistic images, training time becomes a major burden. To overcome this, a segmentation scheme is suggested. Simulation results are also provided.
|
|
Publisher |
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
|
|
Date |
2011-08-01T04:39:38Z
2011-12-26T12:53:16Z 2011-12-27T05:40:31Z 2011-08-01T04:39:38Z 2011-12-26T12:53:16Z 2011-12-27T05:40:31Z 1993 |
|
Type |
Article
|
|
Identifier |
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 41(5), 2018-2022
1053-587X http://dx.doi.org/10.1109/78.215329 http://dspace.library.iitb.ac.in/xmlui/handle/10054/8345 http://hdl.handle.net/10054/8345 |
|
Language |
en
|
|