Extraction of Digital Wavefront Sets Using Applied Harmonic Analysis and Deep Neural Networks

DOI10.1137/19M1237594zbMath1439.35009arXiv1901.01388OpenAlexW2989417853WikidataQ126809614 ScholiaQ126809614MaRDI QIDQ5109278

Ozan Öktem, Philipp Petersen, Gitta Kutyniok, Héctor Andrade-Loarca

Publication date: 11 May 2020

Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1901.01388

zbMATH Keywords

shearletsconvolutional neural networksdeep learning

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Numerical methods for wavelets (65T60) Wave front sets in context of PDEs (35A18)

Related Items (10)

Microlocal analysis and characterization of Sobolev wavefront sets using shearlets ⋮ Deep learning for inverse problems. Abstracts from the workshop held March 7--13, 2021 (hybrid meeting) ⋮ Deep microlocal reconstruction for limited-angle tomography ⋮ Task adapted reconstruction for inverse problems ⋮ An introduction to the mathematics of deep learning ⋮ Edge, Ridge, and Blob Detection with Symmetric Molecules ⋮ On Learning the Invisible in Photoacoustic Tomography with Flat Directionally Sensitive Detector ⋮ The mathematics of artificial intelligence ⋮ Shearlets as feature extractor for semantic edge detection: the model-based and data-driven realm ⋮ Solving inverse problems using data-driven models

Uses Software

• ImageNet
• AlexNet
• CASENet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Resolution of the wavefront set using general continuous wavelet transforms
• Classification of edges using compactly supported shearlets
• Continuous shearlet frames and resolution of the wavefront set
• Variational methods in imaging
• Edge analysis and identification using the continuous shearlet transform
• Analysis of edge and corner points using parabolic dictionaries
• Fourier integral operators. I
• Continuous curvelet transform. I: Resolution of the wavefront set
• Efficient graph-based image segmentation
• The inverse problem for the local geodesic ray transform
• Inferring surfaces from images
• Microlocal Analysis in Tomography
• ShearLab 3D
• Digital Shearlet Transforms
• The Ill-Conditioned Nature of the Limited Angle Tomography Problem
• Singularities of the X-Ray Transform and Limited Data Tomography in $\mathbb{R}^2 $ and $\mathbb{R}^3 $
• Local Tomography in Electron Microscopy
• Fast Computation of Fourier Integral Operators
• Resolution of the wavefront set using continuous shearlets
• Inversion of cone-beam data and helical tomography
• Solving inverse problems using data-driven models
• A Shearlet Approach to Edge Analysis and Detection
• Learning the invisible: a hybrid deep learning-shearlet framework for limited angle computed tomography

This page was built for publication: Extraction of Digital Wavefront Sets Using Applied Harmonic Analysis and Deep Neural Networks