Ultrasound Image Denoising via Dictionary Learning and Total Variation Regularization
Shuai Li, Ximei Zhao
Available Online December 2015.
- https://doi.org/10.2991/icmmcce-15.2015.84How to use a DOI?
- Image Denoising; Multiplicative Noise; Dictionary Learning; TV Regularization; Ultrasound Image
- 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.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
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 - https://doi.org/10.2991/icmmcce-15.2015.84 ID - Li2015/12 ER -