DSpace at IIT Bombay >
IITB Publications >
Please use this identifier to cite or link to this item:
|Title: ||IMAGE-RESTORATION USING A MULTILAYER PERCEPTRON WITH A MULTILEVEL SIGMOIDAL FUNCTION|
|Authors: ||SIVAKUMAR, K|
|Issue Date: ||1993|
|Publisher: ||IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC|
|Citation: ||IEEE TRANSACTIONS ON SIGNAL PROCESSING, 41(5), 2018-2022|
|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 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.|
|Appears in Collections:||Article|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.