Image reconstruction from projections under wavelet constraints

Abstract

First, the authors discuss how the wavelet transform can be used to perform spatially-varying filtering of an image, suppressing noise locally in smooth regions of the image, and discuss detection of such regions in a noise-corrupted image. Second, they show how to compute the minimum mean-square estimate of an image given: (1) noisy projections of the image; (2) statistics of additive noise in the projections; and (3) constraints on wavelet coefficients of the image. Examples illustrate the resulting procedure.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>