Share Email Print

Proceedings Paper

Use of learned dictionaries in tomographic reconstruction
Author(s): Vincent Etter; Ivana Jovanovic; Martin Vetterli
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We study the use and impact of a dictionary in a tomographic reconstruction setup. First, we build two different dictionaries: one using a set of bases functions (Discrete Cosine Transform), and the other that is learned using patches extracted from training images, similar to the image that we would like to reconstruct. We use K-SVD as the learning algorithm. These dictionaries being local, we convert them to global dictionaries, ready to be applied on whole images, by generating all possible shifts of each atom across the image. During the reconstruction, we minimize the reconstruction error by performing a gradient descent on the image representation in the dictionary space. Our experiments show promising results, allowing to eliminate standard artifacts in the tomographic reconstruction, and to reduce the number of measurements required for the inversion. However, the quality of the results depends on the convergence of the learning process, and on the parameters of the dictionaries (number of atoms, convergence criterion, atom size, etc.). The exact influence of each of these remains to be studied.

Paper Details

Date Published: 27 September 2011
PDF: 11 pages
Proc. SPIE 8138, Wavelets and Sparsity XIV, 81381C (27 September 2011); doi: 10.1117/12.894776
Show Author Affiliations
Vincent Etter, Ecole Polytechnique Fédérale de Lausanne (Switzerland)
Ivana Jovanovic, Ecole Polytechnique Fédérale de Lausanne (Switzerland)
Univ. of Geneva (Switzerland)
Martin Vetterli, Ecole Polytechnique Fédérale de Lausanne (Switzerland)

Published in SPIE Proceedings Vol. 8138:
Wavelets and Sparsity XIV
Manos Papadakis; Dimitri Van De Ville; Vivek K. Goyal, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?