Multiresolutional Hybrid NLM-Wieneг Filters for X-Ray Image Denoising

With the rapid evolution of computing and data storage technology, medical image denoising techniques have undergone significant improvement in recent years. Much of this success is in fact due to the emergence of multiresolution analysis (MRA) on both mathematical and algorithmic levels. In this ar...

Full description

Saved in:
Bibliographic Details
Main Authors: Rabbouch, Hana, Saadaoui, Foued, Ibrahim, Hela, Zrigui, Mounir
Format: Conference Proceeding
Language:English
Subjects:
Empirical Mode Decomposition
Empirical Wavelet Transform
Filtering algorithms
Hybrid Filtering
Image resolution
Medical Imaging
Multiresolution Analysis
Noise reduction
Three-dimensional displays
Tomography
Wavelet transforms
X-ray imaging
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the rapid evolution of computing and data storage technology, medical image denoising techniques have undergone significant improvement in recent years. Much of this success is in fact due to the emergence of multiresolution analysis (MRA) on both mathematical and algorithmic levels. In this article, we propose a hybrid multiresolution denoising approach coupling the two filters Non-Local Means and Wiener as well as a multiscale decomposition approach. A comparative study is carried out between two among the best-known MRA-based decomposition techniques: empirical mode decomposition (EMD) and empirical wavelet transform (EWT). Simulations in a denoising framework of a sample of benchmark X-ray images prove the effectiveness of multiscale denoising, especially when hybrid filtering is coupled to EWT. These results give several signs of their ability to be integrated into real-use scanners in the next few years.
ISSN:2576-3555
DOI:10.1109/CoDIT55151.2022.9804037