Lecture Notes in Computer Science, 1993, Volume 719/1993, 118-122, DOI: 10.1007/3-540-57233-3_15

A linear predictor as a regularization function in adaptive image restoration and reconstruction

Bernhard Bundschuh

View Related Documents

Abstract

This paper presents a new algorithm for the restoration and reconstruction of images. A linear predictor provides the regularization function. An adaptive version of the algorithm is developed by matching a weighting function to the previously selected regularization function. The adaptive regularization simultaneously leads to proper noise suppression and enhanced resolution of discontinuities.

Fulltext Preview

Image of the first page of the fulltext document