The phase unwrapping of under-sampled interferograms using radial basis function neural networks

• URL: http://arxiv.org/abs/2210.10541v1
• Date: Wed, 19 Oct 2022 13:30:38 GMT
• Title: The phase unwrapping of under-sampled interferograms using radial basis function neural networks
• Authors: Pierre-Alexandre Gourdain, Aidan Bachmann
• Abstract summary: A neural network is designed to unwrap the phase from two-dimensional interferograms. The network can be trained in parallel and in three stages, using gradient-based supervised learning.
• Score: 9.542104521099937
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Interferometry can measure the shape or the material density of a system that could not be measured otherwise by recording the difference between the phase change of a signal and a reference phase. This difference is always between $-\pi$ and $\pi$ while it is the absolute phase that is required to get a true measurement. There is a long history of methods designed to recover accurately this phase from the phase "wrapped" inside $]-\pi,\pi]$. However, noise and under-sampling limit the effectiveness of most techniques and require highly sophisticated algorithms that can process imperfect measurements. Ultimately, analysing successfully an interferogram amounts to pattern recognition, a task where radial basis function neural networks truly excel at. The proposed neural network is designed to unwrap the phase from two-dimensional interferograms, where aliasing, stemming from under-resolved regions, and noise levels are significant. The neural network can be trained in parallel and in three stages, using gradient-based supervised learning. Parallelism allows to handle relatively large data sets, but requires a supplemental step to synchronized the fully unwrapped phase across the different networks.

Related papers

• 3D-2D Neural Nets for Phase Retrieval in Noisy Interferometric Imaging [0.0]
  We introduce a 3D-2D Phase Retrieval U-Net (PRUNe) that takes noisy and randomly phase-shifted interferograms as inputs, and outputs a single 2D phase image. A 3D downsampling convolutional encoder captures correlations within and between frames to produce a 2D latent space, which is upsampled by a 2D decoder into a phase image. We find PRUNe reconstructions consistently show more accurate and smooth reconstructions, with a x2.5 - 4 lower mean squared error at multiple signal-to-noise ratios for interferograms with low (
  arXiv  Detail & Related papers  (2024-02-08T21:19:16Z)
• Coordinate-based Neural Network for Fourier Phase Retrieval [8.827173113748703]
  Single impliCit neurAl Network (SCAN) is a tool built upon coordinate neural networks meticulously designed for enhanced phase retrieval performance. SCAN adeptly connects object coordinates to their amplitude and phase within a unified network in an unsupervised manner.
  arXiv  Detail & Related papers  (2023-11-25T04:23:23Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data [63.34506218832164]
  In this work, we investigate the implicit bias of gradient flow and gradient descent in two-layer fully-connected neural networks with ReLU activations. For gradient flow, we leverage recent work on the implicit bias for homogeneous neural networks to show that leakyally, gradient flow produces a neural network with rank at most two. For gradient descent, provided the random variance is small enough, we show that a single step of gradient descent suffices to drastically reduce the rank of the network, and that the rank remains small throughout training.
  arXiv  Detail & Related papers  (2022-10-13T15:09:54Z)
• SignalNet: A Low Resolution Sinusoid Decomposition and Estimation Network [79.04274563889548]
  We propose SignalNet, a neural network architecture that detects the number of sinusoids and estimates their parameters from quantized in-phase and quadrature samples. We introduce a worst-case learning threshold for comparing the results of our network relative to the underlying data distributions. In simulation, we find that our algorithm is always able to surpass the threshold for three-bit data but often cannot exceed the threshold for one-bit data.
  arXiv  Detail & Related papers  (2021-06-10T04:21:20Z)
• DeepPhaseCut: Deep Relaxation in Phase for Unsupervised Fourier Phase Retrieval [31.380061715549584]
  We propose a novel, unsupervised, feed-forward neural network for Fourier phase retrieval. Unlike the existing deep learning approaches that use a neural network as a regularization term or an end-to-end blackbox model for supervised training, our algorithm is a feed-forward neural network implementation of PhaseCut algorithm in an unsupervised learning framework. Our network is composed of two generators: one for the phase estimation using PhaseCut loss, followed by another generator for image reconstruction, all of which are trained simultaneously using a cycleGAN framework without matched data.
  arXiv  Detail & Related papers  (2020-11-20T16:10:08Z)
• Solving Sparse Linear Inverse Problems in Communication Systems: A Deep Learning Approach With Adaptive Depth [51.40441097625201]
  We propose an end-to-end trainable deep learning architecture for sparse signal recovery problems. The proposed method learns how many layers to execute to emit an output, and the network depth is dynamically adjusted for each task in the inference phase.
  arXiv  Detail & Related papers  (2020-10-29T06:32:53Z)
• A Joint Convolutional and Spatial Quad-Directional LSTM Network for Phase Unwrapping [7.716156977428555]
  We introduce a novel Convolutional Neural Network (CNN) that incorporates a Spatial Quad-Directional Long Short Term Memory (SQD-LSTM) for phase unwrapping. The proposed network is found to be performing better than the existing methods under severe noise conditions.
  arXiv  Detail & Related papers  (2020-10-26T01:04:19Z)
• Analytic Signal Phase in $N-D$ by Linear Symmetry Tensor--fingerprint modeling [69.35569554213679]
  We show that the Analytic Signal phase, and its gradient have a hitherto unstudied discontinuity in $2-D $ and higher dimensions. This shortcoming can result in severe artifacts whereas the problem does not exist in $1-D $ signals. We suggest the use of Linear Symmetry phase, relying on more than one set of Gabor filters, but with a negligible computational add-on.
  arXiv  Detail & Related papers  (2020-05-16T21:17:26Z)
• MetricUNet: Synergistic Image- and Voxel-Level Learning for Precise CT Prostate Segmentation via Online Sampling [66.01558025094333]
  We propose a two-stage framework, with the first stage to quickly localize the prostate region and the second stage to precisely segment the prostate. We introduce a novel online metric learning module through voxel-wise sampling in the multi-task network. Our method can effectively learn more representative voxel-level features compared with the conventional learning methods with cross-entropy or Dice loss.
  arXiv  Detail & Related papers  (2020-05-15T10:37:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.