Talks given at NuHAG events

An Adaptive Thresholding Algorithm for 3D Images Denoising

  Damiana Lazzaro
    Department of mathematics,University of Bologna

  given at  strobl07 (17.06.07)
  id:  729
  length:  min
  status:  accepted
  type:  poster
\title{An Adaptive Thresholding Algorithm for 3D Images Denoising}
L. B. Montefusco, C. Guerrini, D.Lazzaro
Department of Mathematics, University of

Reducing noise in images is a preliminary step in many image processing applications.
In this work a method for edge-preserving denoising of three dimensional image data
is presented. It is based on the 3D generalization of the dyadic wavelet transform and
overcomes the problems presented by the extension to higher dimensions of the classical
orthogonal wavelet transforms. In fact, a straightforward extension of these separable
transforms to multidimensional data gives very poor results, due to the lack of translation
invariance that produces undesired artifacts. On the contrary, dyadic wavelets are truly
multidimensional translation invariant bases, and the coefficients of the dyadic expansion
of an image {\it f} at different scales contain informations of the gradient of {\it f} smoothed
according to the scale. By integrating these geometric informations in the smoothing
process we obtain a 3D denoising algorithm capable to preserve as much as possible of the
signal features while reducing the noise to a sufficiently low level.

Enter here the CODE for editing this talk:
If you have forgotten the CODE for your talk click here to send an email to the Webmaster!
NOTICE: In [EDIT-MODUS] you can also UPLOAD a presentation"