Results 11 to 20 of about 430 (164)
Normalized group activations based feature extraction technique using heterogeneous data for Alzheimer’s disease classification [PDF]
PeerJ Computer ScienceSeveral deep learning networks are developed to identify the complex atrophic patterns of Alzheimer's disease (AD). Among various activation functions used in deep neural networks, the rectifier linear unit is the most used one.
Krishnakumar Vaithianathan +5 more
doaj +3 more sources
A model-based image fusion framework using discrete band-limited shearlets [PDF]
Scientific ReportsThe limited dynamic range of digital imaging sensors often leads to under- or over-exposed images. While deep learning methods currently dominate multi-exposure image fusion (MEF), they suffer from data dependency and poor interpretability.
Wentao Ji, Xing Chen
doaj +2 more sources
Shearlets as feature extractor for semantic edge detection: the model-based and data-driven realm. [PDF]
Proc Math Phys Eng Sci, 2020 Semantic edge detection has recently gained a lot of attention as an image-processing task, mainly because of its wide range of real-world applications. This is based on the fact that edges in images contain most of the semantic information.
Andrade-Loarca H, Kutyniok G, Öktem O.
europepmc +2 more sources
ACM Transactions on Mathematical Software, 2016 Wavelets and their associated transforms are highly efficient when approximating and analyzing one-dimensional signals. However, multivariate signals such as images or videos typically exhibit curvilinear singularities, which wavelets are provably deficient in sparsely approximating and also in analyzing in the sense of, for instance, detecting their ...
Gitta Kutyniok +2 more
core +7 more sources
Mathematics, 2020 The discrete wavelet transform (DWT) is unable to represent the directional features of an image. Similarly, a fixed embedding strength is not able to establish an ideal balance between imperceptibility and robustness of a watermarked image. In this work,
Qiumei Zheng, Nan Liu, Fenghua Wang
doaj +2 more sources
Homogeneous approximation property for continuous shearlet transforms in higher dimensions [PDF]
Journal of Inequalities and Applications, 2016 This paper is concerned with the generalization of the homogeneous approximation property (HAP) for a continuous shearlet transform to higher dimensions. First, we give a pointwise convergence result on the inverse shearlet transform in higher dimensions.
Yu Su, Wanchang Zhang, Wenting Su
doaj +2 more sources
Обработка изображений с помощью Shearlets [PDF]
, 2020 В статье дано определение и основные возможности для приложений Shearlets. Рассматривается проблема удаления шума с изображения с по- мощью вейвлетов и Shearlets.
Захарова, А. А. +1 more
core +2 more sources
IEEE Access, 2017 Sparsity is one of the key concepts that allows the signal recovery at a significantly lower subsample rate than required by the Nyquist-Shannon sampling theorem.
Guomin Sun, Jinsong Leng, Tingzhu Huang
doaj +1 more source
Shearlet Coorbit Spaces: Compactly Supported Analyzing Shearlets, Traces and Embeddings [PDF]
Journal of Fourier Analysis and Applications, 2011 The authors show that compactly supported functions with sufficient smoothness and enough vanishing moments can serve as analyzing vectors for shearlet coorbit space. This approach has bee used to prove embedding theorems for subspaces of shearlet coorbit spaces resembling shearlets on the cone into Besov spaces.
Dahlke, Stephan +2 more
openaire +2 more sources
Variational Multiscale Nonparametric Regression: Algorithms and Implementation
Algorithms, 2020 Many modern statistically efficient methods come with tremendous computational challenges, often leading to large-scale optimisation problems. In this work, we examine such computational issues for recently developed estimation methods in nonparametric ...
Miguel del Alamo +3 more
doaj +1 more source