A Stochastic Method For Ultrasound Despeckling In Images Via Dynamic Weight Allocation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F18%3APU128488" target="_blank" >RIV/00216305:26220/18:PU128488 - isvavai.cz</a>
Result on the web
<a href="http://tsp.vutbr.cz/datas/tsp2018_proc/TSP2018.pdf" target="_blank" >http://tsp.vutbr.cz/datas/tsp2018_proc/TSP2018.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
A Stochastic Method For Ultrasound Despeckling In Images Via Dynamic Weight Allocation
Original language description
Medical and biological imaging modalities like ultrasound often contain noise that is non-linear in nature. Noise reduction via linear filtering algorithms often produce unimpressive results. Multiplicative noise like speckle noise is inherently present in medical ultrasound images, and it usually reduces the contrast between region of interest and the background. Recent algorithms like Bayesian methods have been used with some degree of success but they are computationally intensive. This paper presents an iterative algorithm for noise reduction in ultrasound images via dynamic weight allocation. Proposed method is fast and performs better in comparison to state-of-art techniques.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20201 - Electrical and electronic engineering
Result continuities
Project
<a href="/en/project/GA17-19638S" target="_blank" >GA17-19638S: Sequential Bayesian Estimation of Arterial Wall Motion</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 2018 41st International Conference on Telecommunications and Signal Processing
ISBN
978-1-5386-4695-3
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
228-231
Publisher name
Faculty of Electrical Engineering and Communacation, Brno University of Technology
Place of publication
Technická 3058/10, 616 00 Brno, Czech Republic
Event location
Athens, Greece
Event date
Jul 4, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000454845100053