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 co...Show MoreMetadata
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 nonlinearlity. 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 provided.<>
Published in: IEEE Transactions on Signal Processing ( Volume: 41, Issue: 5, May 1993)
DOI: 10.1109/78.215329