scholarly journals Inverse Synthetic Aperture Radar Sparse Imaging Exploiting the Group Dictionary Learning

2021 ◽  
Vol 13 (14) ◽  
pp. 2812
Author(s):  
Changyu Hu ◽  
Ling Wang ◽  
Daiyin Zhu ◽  
Otmar Loffeld
Keyword(s):  
Image Reconstruction ◽  
Dictionary Learning ◽  
Reconstruction Error ◽  
Imaging Method ◽  
L1 Norm ◽  
Norm Minimization ◽  
Imaging Results ◽  
Computational Speed ◽  
Feature Information ◽  
The Relationship

Sparse imaging relies on sparse representations of the target scenes to be imaged. Predefined dictionaries have long been used to transform radar target scenes into sparse domains, but the performance is limited by the artificially designed or existing transforms, e.g., Fourier transform and wavelet transform, which are not optimal for the target scenes to be sparsified. The dictionary learning (DL) technique has been exploited to obtain sparse transforms optimized jointly with the radar imaging problem. Nevertheless, the DL technique is usually implemented in a manner of patch processing, which ignores the relationship between patches, leading to the omission of some feature information during the learning of the sparse transforms. To capture the feature information of the target scenes more accurately, we adopt image patch group (IPG) instead of patch in DL. The IPG is constructed by the patches with similar structures. DL is performed with respect to each IPG, which is termed as group dictionary learning (GDL). The group oriented sparse representation (GOSR) and target image reconstruction are then jointly optimized by solving a l1 norm minimization problem exploiting GOSR, during which a generalized Gaussian distribution hypothesis of radar image reconstruction error is introduced to make the imaging problem tractable. The imaging results using the real ISAR data show that the GDL-based imaging method outperforms the original DL-based imaging method in both imaging quality and computational speed.

scholarly journals Gradient Projection with Approximate L0 Norm Minimization for Sparse Reconstruction in Compressed Sensing

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3373 ◽  
Author(s):  
Ziran Wei ◽  
Jianlin Zhang ◽  
Zhiyong Xu ◽  
Yongmei Huang ◽  
Yong Liu ◽  
...  
Keyword(s):  
Image Reconstruction ◽  
Compressed Sensing ◽  
Objective Function ◽  
Signal Reconstruction ◽  
Reconstruction Error ◽  
Sparse Signal ◽  
Reconstruction Accuracy ◽  
L1 Norm ◽  
Function Model ◽  
L2 Norm

In the reconstruction of sparse signals in compressed sensing, the reconstruction algorithm is required to reconstruct the sparsest form of signal. In order to minimize the objective function, minimal norm algorithm and greedy pursuit algorithm are most commonly used. The minimum L1 norm algorithm has very high reconstruction accuracy, but this convex optimization algorithm cannot get the sparsest signal like the minimum L0 norm algorithm. However, because the L0 norm method is a non-convex problem, it is difficult to get the global optimal solution and the amount of calculation required is huge. In this paper, a new algorithm is proposed to approximate the smooth L0 norm from the approximate L2 norm. First we set up an approximation function model of the sparse term, then the minimum value of the objective function is solved by the gradient projection, and the weight of the function model of the sparse term in the objective function is adjusted adaptively by the reconstruction error value to reconstruct the sparse signal more accurately. Compared with the pseudo inverse of L2 norm and the L1 norm algorithm, this new algorithm has a lower reconstruction error in one-dimensional sparse signal reconstruction. In simulation experiments of two-dimensional image signal reconstruction, the new algorithm has shorter image reconstruction time and higher image reconstruction accuracy compared with the usually used greedy algorithm and the minimum norm algorithm.

scholarly journals Two-Dimensional l1-Norm Minimization in SAR Image Reconstriction

2015 ◽  
Vol 15 (7) ◽  
pp. 77-87
Author(s):  
A. Lazarov ◽  
D. Minchev
Keyword(s):  
Image Reconstruction ◽  
Sar Image ◽  
Two Dimensional ◽  
Reconstruction Problem ◽  
L1 Norm ◽  
One Dimensional ◽  
Sparse Decomposition ◽  
Norm Minimization ◽  
The Earth ◽  
Definition Of

Abstract A nonconventional image algorithm, based on compressed sensing and l1-norm minimization in Synthetic Aperture Radar (SAR) application is discussed. A discrete model of the earth surface relief and mathematical modeling of SAR signal formation are analytically described. Sparse decomposition in Fourier basis to solve the SAR image reconstruction problem is discussed. In contrast to the classical one-dimensional definition of l1-norm minimization in SAR image reconstruction, applied to an image vector, the present work proposes a two-dimensional definition of l1-norm minimization to the image. To verify the correctness of the algorithm, results of numerical experiments are presented.

scholarly journals A Photoacoustic Imaging Algorithm Based on Regularized Smoothed L0 Norm Minimization

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Xueyan Liu ◽  
Limei Zhang ◽  
Yining Zhang ◽  
Lishan Qiao
Keyword(s):  
Image Reconstruction ◽  
Photoacoustic Imaging ◽  
Sparse Sampling ◽  
Signal Recovery ◽  
L1 Norm ◽  
High Quality ◽  
Norm Minimization ◽  
Reconstruction Quality ◽  
Noisy Measurement ◽  
Better Than

The recently emerging technique of sparse reconstruction has received much attention in the field of photoacoustic imaging (PAI). Compressed sensing (CS) has large potential in efficiently reconstructing high-quality PAI images with sparse sampling signal. In this article, we propose a CS-based error-tolerant regularized smooth L0 (ReSL0) algorithm for PAI image reconstruction, which has the same computational advantages as the SL0 algorithm while having a higher degree of immunity to inaccuracy caused by noise. In order to evaluate the performance of the ReSL0 algorithm, we reconstruct the simulated dataset obtained from three phantoms. In addition, a real experimental dataset from agar phantom is also used to verify the effectiveness of the ReSL0 algorithm. Compared to three L0 norm, L1 norm, and TV norm-based CS algorithms for signal recovery and image reconstruction, experiments demonstrated that the ReSL0 algorithm provides a good balance between the quality and efficiency of reconstructions. Furthermore, the PSNR of the reconstructed image calculated by the introduced method was better than the other three methods. In particular, it can notably improve reconstruction quality in the case of noisy measurement.

scholarly journals Analysis and Mapping of Detailed Inner Information of Crystalline Grain by Wavelength-Resolved Neutron Transmission Imaging with Individual Bragg-Dip Profile-Fitting Analysis

2021 ◽  
Vol 11 (11) ◽  
pp. 5219
Author(s):  
Yosuke Sakurai ◽  
Hirotaka Sato ◽  
Nozomu Adachi ◽  
Satoshi Morooka ◽  
Yoshikazu Todaka ◽  
...  
Keyword(s):  
Crystal Orientation ◽  
Perfect Crystal ◽  
Imaging Method ◽  
Transmission Imaging ◽  
Profile Fitting ◽  
Imaging Results ◽  
Integrated Intensity ◽  
Small Change ◽  
Integrated Intensities ◽  
Pulsed Neutron

As a new method for evaluating single crystals and oligocrystals, pulsed neutron Bragg-dip transmission analysis/imaging method is being developed. In this study, a single Bragg-dip profile-fitting analysis method was newly developed, and applied for analyzing detailed inner information in a crystalline grain position-dependently. In the method, the spectrum profile of a single Bragg-dip is analyzed at each position over a grain. As a result, it is expected that changes in crystal orientation, mosaic spread angle and thickness of a perfect crystal can be evaluated from the wavelength, the width and the integrated intensity of the Bragg-dip, respectively. For confirming this effectiveness, the method was applied to experimental data of position-dependent Bragg-dip transmission spectra of a Si-steel plate consisting of oligocrystals. As a result, inner information of multiple crystalline grains could be visualized and evaluated. The small change in crystal orientation in a grain, about 0.4°, could be observed by imaging the Bragg-dip wavelengths. By imaging the Bragg-dip widths, both another grain and mosaic block in a grain were detected. Furthermore, imaging results of the integrated intensities of Bragg-dips were consistent with the results of Bragg-dip width imaging. These small crystallographic changes have not been observed and visualized by previous Bragg-dip analysis methods.

scholarly journals Adaptive hyperparameter updating for training restricted Boltzmann machines on quantum annealers

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Guanglei Xu ◽  
William S. Oates
Keyword(s):  
Neural Network ◽  
Maximum Likelihood ◽  
Image Reconstruction ◽  
Image Recognition ◽  
Shannon Entropy ◽  
Reconstruction Error ◽  
Likelihood Method ◽  
Restricted Boltzmann Machines ◽  
Boltzmann Machines ◽  
D Wave

AbstractRestricted Boltzmann Machines (RBMs) have been proposed for developing neural networks for a variety of unsupervised machine learning applications such as image recognition, drug discovery, and materials design. The Boltzmann probability distribution is used as a model to identify network parameters by optimizing the likelihood of predicting an output given hidden states trained on available data. Training such networks often requires sampling over a large probability space that must be approximated during gradient based optimization. Quantum annealing has been proposed as a means to search this space more efficiently which has been experimentally investigated on D-Wave hardware. D-Wave implementation requires selection of an effective inverse temperature or hyperparameter ($$\beta $$ β ) within the Boltzmann distribution which can strongly influence optimization. Here, we show how this parameter can be estimated as a hyperparameter applied to D-Wave hardware during neural network training by maximizing the likelihood or minimizing the Shannon entropy. We find both methods improve training RBMs based upon D-Wave hardware experimental validation on an image recognition problem. Neural network image reconstruction errors are evaluated using Bayesian uncertainty analysis which illustrate more than an order magnitude lower image reconstruction error using the maximum likelihood over manually optimizing the hyperparameter. The maximum likelihood method is also shown to out-perform minimizing the Shannon entropy for image reconstruction.

Preoperative identification of the facial nerve in patients with large cerebellopontine angle tumors using high-density diffusion tensor imaging

2012 ◽  
Vol 116 (4) ◽  
pp. 697-702 ◽  
Author(s):  
Neil Roundy ◽  
Johnny B. Delashaw ◽  
Justin S. Cetas
Keyword(s):  
Diffusion Tensor Imaging ◽  
Facial Nerve ◽  
Cerebellopontine Angle ◽  
Diffusion Tensor ◽  
Tumor Resection ◽  
High Density ◽  
Imaging Method ◽  
Study Objective ◽  
Nerve Preservation ◽  
Imaging Results

Object Facial nerve paresis can be a devastating complication following resection of large (> 2.5 cm) cerebellopontine angle (CPA) tumors. The authors have developed and used a new high-density diffusion tensor imaging (HD-DT imaging) method, aimed at preoperatively identifying the location and course of the facial nerve in relation to large CPA tumors. Their study objective was to preoperatively identify the facial nerve in patients with large CPA tumors and compare their HD-DT imaging method with a traditional standard DT imaging method and correlate with intraoperative findings. Methods The authors prospectively studied 5 patients with large (> 2.5 cm) CPA tumors. All patients underwent preoperative traditional standard- and HD-DT imaging. Imaging results were correlated with intraoperative findings. Results Utilizing their HD-DT imaging method, the authors positively identified the location and course of the facial nerve in all patients. In contrast, using a standard DT imaging method, the authors were unable to identify the facial nerve in 4 of the 5 patients. Conclusions The HD-DT imaging method that the authors describe and use has proven to be a powerful, accurate, and rapid method for preoperatively identifying the facial nerve in relation to large CPA tumors. Routine integration of HD-DT imaging in preoperative planning for CPA tumor resection could lead to improved facial nerve preservation.

Accelerated 3D blind separation of convolved mixtures based on the fast iterative shrinkage thresholding algorithm for adaptive multiple subtraction

Geophysics ◽  
2018 ◽  
Vol 83 (2) ◽  
pp. V99-V113 ◽  
Author(s):  
Zhong-Xiao Li ◽  
Zhen-Chun Li
Keyword(s):  
Field Data ◽  
Optimization Problem ◽  
Computational Cost ◽  
Computation Time ◽  
Blind Separation ◽  
L1 Norm ◽  
Norm Minimization ◽  
Iterative Shrinkage ◽  
Thresholding Algorithm ◽  
Iterative Shrinkage Thresholding

After multiple prediction, adaptive multiple subtraction is essential for the success of multiple removal. The 3D blind separation of convolved mixtures (3D BSCM) method, which is effective in conducting adaptive multiple subtraction, needs to solve an optimization problem containing L1-norm minimization constraints on primaries by the iterative reweighted least-squares (IRLS) algorithm. The 3D BSCM method can better separate primaries and multiples than the 1D/2D BSCM method and the method with energy minimization constraints on primaries. However, the 3D BSCM method has high computational cost because the IRLS algorithm achieves nonquadratic optimization with an LS optimization problem solved in each iteration. In general, it is good to have a faster 3D BSCM method. To improve the adaptability of field data processing, the fast iterative shrinkage thresholding algorithm (FISTA) is introduced into the 3D BSCM method. The proximity operator of FISTA can solve the L1-norm minimization problem efficiently. We demonstrate that our FISTA-based 3D BSCM method achieves similar accuracy of estimating primaries as that of the reference IRLS-based 3D BSCM method. Furthermore, our FISTA-based 3D BSCM method reduces computation time by approximately 60% compared with the reference IRLS-based 3D BSCM method in the synthetic and field data examples.

scholarly journals Phaseless Imaging by Reverse Time Migration: Acoustic Waves

2017 ◽  
Vol 10 (1) ◽  
pp. 1-21 ◽  
Author(s):  
Zhiming Chen ◽  
Guanghui Huang
Keyword(s):  
Acoustic Waves ◽  
Numerical Experiments ◽  
Cross Correlation ◽  
Scattering Data ◽  
Imaging Method ◽  
Total Field ◽  
Reverse Time ◽  
Reverse Time Migration ◽  
Time Migration ◽  
Imaging Results

AbstractWe propose a reliable direct imaging method based on the reverse time migration for finding extended obstacles with phaseless total field data. We prove that the imaging resolution of the method is essentially the same as the imaging results using the scattering data with full phase information when the measurement is far away from the obstacle. The imaginary part of the cross-correlation imaging functional always peaks on the boundary of the obstacle. Numerical experiments are included to illustrate the powerful imaging quality

scholarly journals A Benchmark Dataset and Deep Learning-Based Image Reconstruction for Electrical Capacitance Tomography

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3701 ◽  
Author(s):  
Jin Zheng ◽  
Jinku Li ◽  
Yi Li ◽  
Lihui Peng
Keyword(s):  
Machine Learning ◽  
Image Reconstruction ◽  
Benchmark Dataset ◽  
Electrical Capacitance Tomography ◽  
Electrical Capacitance ◽  
Reconstruction Algorithms ◽  
Reconstruction Methods ◽  
Image Reconstruction Algorithms ◽  
Capacitance Tomography ◽  
The Relationship

Electrical Capacitance Tomography (ECT) image reconstruction has developed for decades and made great achievements, but there is still a need to find a new theoretical framework to make it better and faster. In recent years, machine learning theory has been introduced in the ECT area to solve the image reconstruction problem. However, there is still no public benchmark dataset in the ECT field for the training and testing of machine learning-based image reconstruction algorithms. On the other hand, a public benchmark dataset can provide a standard framework to evaluate and compare the results of different image reconstruction methods. In this paper, a benchmark dataset for ECT image reconstruction is presented. Like the great contribution of ImageNet that transformed machine learning research, this benchmark dataset is hoped to be helpful for society to investigate new image reconstruction algorithms since the relationship between permittivity distribution and capacitance can be better mapped. In addition, different machine learning-based image reconstruction algorithms can be trained and tested by the unified dataset, and the results can be evaluated and compared under the same standard, thus, making the ECT image reconstruction study more open and causing a breakthrough.

Sign in / Sign up

Export Citation Format

Share Document