Spatially Adaptive Image Restoration by Neural Network Filtering

Alex S. PalmerMoe RazazDanilo P. Mandic

When using a regularized approach for image restora-tion 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 spa-tially 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.

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: