Results 51 to 60 of about 413 (120)

An EfficientNet integrated ResNet deep network and explainable AI for breast lesion classification from ultrasound images

open access: yesCAAI Transactions on Intelligence Technology, Volume 10, Issue 3, Page 842-857, June 2025.
Abstract Breast cancer is one of the major causes of deaths in women. However, the early diagnosis is important for screening and control the mortality rate. Thus for the diagnosis of breast cancer at the early stage, a computer‐aided diagnosis system is highly required.
Kiran Jabeen   +6 more
wiley   +1 more source

Computerized tomography with total variation and with shearlets [PDF]

open access: yesInverse Problems, 2017
Abstract To reduce the x-ray dose in computerized tomography (CT), many constrained optimization approaches have been proposed aiming at minimizing a regularizing function that measures a lack of consistency with some prior knowledge about the object that is being imaged, subject to a (predetermined) level of ...
Edgar Garduño, Gabor T. Herman
openaire   +2 more sources

A Time‐Adaptive Diffusion‐Based CT Image Denoising Method by Processing Directional and Non‐Local Information

open access: yesInternational Journal of Imaging Systems and Technology, Volume 35, Issue 2, March 2025.
ABSTRACT Low‐dose computed tomography (CT) images are prone to noise and artifacts caused by photon starvation and electronic noise. Recently, researchers have explored the use of transformer‐based neural networks combined with generative diffusion models, showing promising results in denoising CT images.
Farzan Niknejad Mazandarani   +2 more
wiley   +1 more source

Calderón–Zygmund theory on some Lie groups of exponential growth

open access: yesMathematische Nachrichten, Volume 298, Issue 1, Page 113-141, January 2025.
Abstract Let G=N⋊A$G = N \rtimes A$, where N$N$ is a stratified Lie group and A=R+$A= \mathbb {R}_+$ acts on N$N$ via automorphic dilations. We prove that the group G$G$ has the Calderón–Zygmund property, in the sense of Hebisch and Steger, with respect to a family of flow measures and metrics.
Filippo De Mari   +3 more
wiley   +1 more source

A multi‐path residual network for image denoising based on edge prior information

open access: yesIET Image Processing, Volume 18, Issue 14, Page 4514-4530, 11 December 2024.
To overcome the problem of the smoothness and loss of high‐frequency details at edges in image denoising, a multi‐path residual network using edge prior information is proposed. Firstly, the edge is recovered from the noisy image via the edge extraction module.
Xuefei Bai, Yongsong Wan, Weiming Wang
wiley   +1 more source

Analysis vs. synthesis sparsity for α-shearlets

open access: yes, 2017
There are two notions of sparsity associated to a frame Ψ=(ψi)i∈I: Analysis sparsity of f means that the analysis coefficients (⟨f,ψi⟩)i are sparse, while synthesis sparsity means that f=∑iciψi with sparse coefficients (ci)i.
Pein, Anne, Voigtlaender, Felix
core   +1 more source

Compactly Supported Shearlets [PDF]

open access: yes, 2011
24 pages, 7 figures, Conference Proceeding: Approximation Theory XIII (San Antonio, TX, 2010), Springer (to appear)
Kutyniok, Gitta   +2 more
openaire   +2 more sources

A self‐supervised scheme for ground roll suppression

open access: yesGeophysical Prospecting, Volume 72, Issue 7, Page 2580-2598, September 2024.
Abstract In recent years, self‐supervised procedures have advanced the field of seismic noise attenuation, due to not requiring a massive amount of clean labelled data in the training stage, an unobtainable requirement for seismic data. However, current self‐supervised methods usually suppress simple noise types, such as random and trace‐wise noise ...
Sixiu Liu   +5 more
wiley   +1 more source

Democracy of shearlet frames with applications

open access: yesJournal of Approximation Theory, 2017
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire   +1 more source

Enhancing Signal Discontinuities with Shearlets: An Application to Corner Detection

open access: yes, 2015
Shearlets are a relatively new and very effective multiresolution framework for signal analysis able to capture efficiently the anisotropic information in multivariate problem classes.
Miguel Alejandro Duval-Poo   +5 more
core   +1 more source

Home - About - Disclaimer - Privacy