Spatially adaptive image restoration by neural network filtering

Palmer, A. S., Razaz, M. and Mandic, D. P. (2002) Spatially adaptive image restoration by neural network filtering. In: VII Brazilian Symposium on Neural Networks, 2002-11-11 - 2002-11-14.

Full text not available from this repository.

Abstract

When using a regularized approach for image restoration there is always a compromise between image sharpness and noise suppression. Therefore, the main problem is to remove as much noise as possible while preserving sharpness in the restoration. To this cause we introduce a spatially regularized neural approach that makes use of local image statistics to apply varying regularization to different areas of the image. This is achieved with an efficient parallel implementation of the Hopfield neural network. The proposed approach exhibits an improvement in restoration quality and execution time over the existing approaches. This is illustrated on simulations on benchmark images.

Item Type:	Conference or Workshop Item (Paper)
Faculty \ School:	Faculty of Science > School of Computing Sciences
Depositing User:	Vishal Gautam
Date Deposited:	28 Jul 2011 10:25
Last Modified:	15 Dec 2022 01:05
URI:	https://ueaeprints.uea.ac.uk/id/eprint/21866
DOI:	10.1109/SBRN.2002.1181467

Actions (login required)

View Item