Ultrasound Image Denoising via Dictionary Learning and Total Variation Regularization

DOI

10.2991/icmmcce-15.2015.84How to use a DOI?

Keywords

Image Denoising; Multiplicative Noise; Dictionary Learning; TV Regularization; Ultrasound Image

Abstract

The restoration of images corrupted by speckle noise is a key issue in medical images. In this paper, a novel sparse model is presented for speckle reduction in ultrasound (US) images. This model contains three terms: a patch-based sparse representation prior over dictionary learning, a pixel-based total variation (TV) regularization term, and a data-fidelity term capturing the statistics of Rayleigh noise. The split Bregman algorithm for the proposed model is presented to solve the optimization problem. Experimental results on real US images validate that the proposed method is able to keep accurately edges and preserve meaningful structural details of the images.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shuai Li
AU  - Ximei Zhao
PY  - 2015/12
DA  - 2015/12
TI  - Ultrasound Image Denoising via Dictionary Learning and Total Variation Regularization
BT  - Proceedings of the 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering 2015
PB  - Atlantis Press
SP  - 410
EP  - 416
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmcce-15.2015.84
DO  - 10.2991/icmmcce-15.2015.84
ID  - Li2015/12
ER  -